{"id":13440972,"url":"https://github.com/ZitongYu/DeepFAS","last_synced_at":"2025-03-20T11:34:31.147Z","repository":{"id":37773628,"uuid":"376654099","full_name":"ZitongYu/DeepFAS","owner":"ZitongYu","description":"🔥Deep Learning for Face Anti-Spoofing","archived":false,"fork":false,"pushed_at":"2023-07-11T08:43:28.000Z","size":23667,"stargazers_count":512,"open_issues_count":1,"forks_count":64,"subscribers_count":19,"default_branch":"main","last_synced_at":"2024-08-01T03:32:36.386Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ZitongYu.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-06-13T22:45:28.000Z","updated_at":"2024-08-01T01:11:03.000Z","dependencies_parsed_at":"2023-02-17T21:00:23.196Z","dependency_job_id":null,"html_url":"https://github.com/ZitongYu/DeepFAS","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZitongYu%2FDeepFAS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZitongYu%2FDeepFAS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZitongYu%2FDeepFAS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZitongYu%2FDeepFAS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ZitongYu","download_url":"https://codeload.github.com/ZitongYu/DeepFAS/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221752178,"owners_count":16874941,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-07-31T03:01:28.431Z","updated_at":"2025-03-20T11:34:31.083Z","avatar_url":"https://github.com/ZitongYu.png","language":null,"funding_links":[],"categories":["Others","Uncategorized"],"sub_categories":["Uncategorized"],"readme":"# 👏 Survey of Deep Face Anti-spoofing 🔥\n\nThis is the official repository of \"**[Deep Learning for Face Anti-Spoofing: A Survey](https://arxiv.org/abs/2106.14948)**\", a comprehensive survey \nof recent progress in deep learning methods for face anti-spoofing (FAS) as well as the datasets and protocols.\n\n\n\n### Citation\nIf you find our work useful in your research, please consider citing:\n\n    @article{yu2022deep,\n      title={Deep Learning for Face Anti-Spoofing: A Survey},\n      author={Yu, Zitong and Qin, Yunxiao and Li, Xiaobai and Zhao, Chenxu and Lei, Zhen and Zhao, Guoying},\n      journal={IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},\n      year={2022}\n    }\n\n\n## Introduction\nWe present a comprehensive review of recent deep learning methods for face anti-spoofing (mostly from 2018 to 2022). It covers hybrid (handcrafted+deep), pure deep learning, and generalized learning based methods for monocular RGB face anti-spoofing. It also includes multi-modal learning based methods as well as specialized sensor based FAS. It also presents detailed comparision among publicly available datasets, together with several classical evaluation protocols.\n\n🔔 We will update this page frequently~ :tada::tada::tada:\n\n---\n## Contents\n\n- [Datasets](#data)\n  - [Using commercial RGB camera](#data_RGB)\n  - [With multiple modalities or specialized sensors](#data_Multimodal)\n- [Deep FAS methods with commercial RGB camera](#methods_RGB)\n  - [Hybrid (handcrafted + deep)](#hybrid)\n  - [End-to-end binary cross-entropy supervision](#binary)\n  - [Pixel-wise auxiliary supervision](#auxiliary)\n  - [Generative model with pixel-wise supervision](#generative)\n  - [Domain adaptation](#DA)\n  - [Domain generalization](#DG)\n  - [Zero/Few-shot learning](#zero-shot)\n  - [Anomaly detection](#oneclass)\n  - [Semi-supervision \u0026 Self-supervision](#semiself)\n  - [Continual learning](#CL)\n- [Deep FAS methods with advanced sensor](#methods_advanced)\n  - [Learning upon specialized sensor](#sensor)\n  - [Multi-modal learning](#multimodal)\n  - [Flexible-modal learning](#flexmodal)\n\n---\n  ![image](https://github.com/ZitongYu/DeepFAS/blob/main/Topology.png)   \n  \n---\n\n\n\u003ca name=\"data\" /\u003e\n\n### 1️⃣ Datasets\n\n\u003ca name=\"data_RGB\" /\u003e\n\n#### Datasets recorded with commercial RGB camera\n\n| Dataset    | Year | #Live/Spoof | #Sub. |  Setup | Attack Types |\n| --------   | -----    | -----  |  -----  | ----- |------------------------|\n| [NUAA](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.607.5449\u0026rep=rep1\u0026type=pdf)   | 2010 | 5105/7509(I) | 15 |  N/R | Print(flat, wrapped)|\n| [YALE Recaptured](https://www.ic.unicamp.br/~rocha/pub/papers/2011-icip-spoofing-detection.pdf)   | 2011 | 640/1920(I) | 10 |  50cm-distance from 3 LCD minitors | Print(flat) |\n| [CASIA-MFSD](http://www.cbsr.ia.ac.cn/users/jjyan/ZHANG-ICB2012.pdf)   | 2012 | 150/450(V) | 50 |  7 scenarios and 3 image quality | Print(flat, wrapped, cut), Replay(tablet)|\n| [REPLAY-ATTACK](http://publications.idiap.ch/downloads/papers/2012/Chingovska_IEEEBIOSIG2012_2012.pdf)   | 2012 | 200/1000(V) | 50 |  Lighting and holding | Print(flat), Replay(tablet, phone) |\n| [Kose and Dugelay](https://ieeexplore.ieee.org/document/6595862)   | 2013 | 200/198(I) | 20 |  N/R | Mask(hard resin) |\n| [MSU-MFSD](http://biometrics.cse.msu.edu/Publications/Face/WenHanJain_FaceSpoofDetection_TIFS15.pdf)   | 2014 | 70/210(V) | 35 |  Indoor scenario; 2 types of cameras | Print(flat), Replay(tablet, phone) |\n| [UVAD](https://ieeexplore.ieee.org/document/7017526)   | 2015 | 808/16268(V) | 404 | Different lighting, background and places in two sections | Replay(monitor) |\n| [REPLAY-Mobile](https://ieeexplore.ieee.org/document/7736936)   | 2016 | 390/640(V) | 40 |  5 lighting conditions | Print(flat), Replay(monitor) |\n| [HKBU-MARs V2](https://link.springer.com/chapter/10.1007/978-3-319-46478-7_6)   | 2016 | 504/504(V) | 12 | 7 cameras from stationary and mobile devices and 6 lighting settings | Mask(hard resin) from Thatsmyface and REAL-f |\n| [MSU USSA](https://ieeexplore.ieee.org/document/7487030)   | 2016 | 1140/9120(I) | 1140 |  Uncontrolled; 2 types of cameras | Print(flat), Replay(laptop, tablet, phone)|\n| [SMAD](https://ieeexplore.ieee.org/document/7867821)   | 2017 | 65/65(V) | - |  Color images from online resources | Mask(silicone) |\n| [OULU-NPU](https://ieeexplore.ieee.org/document/7961798)   | 2017 | 720/2880(V) | 55 |  Lighting \u0026 background in 3 sections | Print(flat), Replay(phone) |\n| [Rose-Youtu](https://ieeexplore.ieee.org/document/8279564)   | 2018 | 500/2850(V) | 20 | 5 front-facing phone camera; 5 different illumination conditions | Print(flat), Replay(monitor, laptop),Mask(paper, crop-paper)|\n| [SiW](https://arxiv.org/abs/1803.11097)   | 2018 | 1320/3300(V) | 165 |  4 sessions with variations of distance, pose, illumination and expression | Print(flat, wrapped), Replay(phone, tablet, monitor)|\n| [WFFD](https://arxiv.org/abs/2005.06514)   | 2019 | 2300/2300(I) 140/145(V) | 745 |  Collected online; super-realistic; removed low-quality faces | Waxworks(wax)|\n| [SiW-M](https://openaccess.thecvf.com/content_CVPR_2019/papers/Liu_Deep_Tree_Learning_for_Zero-Shot_Face_Anti-Spoofing_CVPR_2019_paper.pdf)   | 2019 | 660/968(V) | 493 |  Indoor environment with pose, lighting and expression variations | Print(flat), Replay, Mask(hard resin, plastic, silicone, paper, Mannequin), Makeup(cosmetics, impersonation, Obfuscation), Partial(glasses, cut paper)|\n| [Swax](https://arxiv.org/abs/1910.09642)   | 2020 | Total 1812(I) 110(V) | 55 |  Collected online; captured under uncontrolled scenarios | Waxworks(wax)|\n| [CelebA-Spoof](https://link.springer.com/chapter/10.1007/978-3-030-58610-2_5)   | 2020 | 156384/469153(I) | 10177 |  4 illumination conditions; indoor \u0026 outdoor; rich annotations | Print(flat, wrapped), Replay(monitor tablet, phone), Mask(paper)|\n| [RECOD-Mtablet](https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0238058)   | 2020 | 450/1800(V) | 45 | Outdoor environment and low-light \u0026 dynamic sessions | Print(flat), Replay(monitor) |\n| [CASIA-SURF 3DMask](https://ieeexplore.ieee.org/document/9252183)   | 2020 | 288/864(V)  | 48 |  High-quality identity-preserved; 3 decorations and 6 environments | Mask(mannequin with 3D print) |\n| [HiFiMask](https://arxiv.org/abs/2104.06148)   | 2021 | 13650/40950(V) | 75 |  three mask decorations; 7 recording devices; 6 lighting conditions; 6 scenes | Mask(transparent, plaster, resin)|\n| [SiW-M v2](https://github.com/CHELSEA234/Multi-domain-learning-FAS)   | 2022 | 785/915 (V) | 1093(493/600) |  Both indoor and outdoor, diverse age and enthnicity, 7 illumiations | IAPRA-verified 14 spoof attacks (4 coverings, 3 makeups, 3 masks, 2 human models, replay and print)|\n| [SuHiFiMask](https://arxiv.org/abs/2301.00975)   | 2022 | 10195/10195 (V) | 101 |  Long distance using Surveillance cameras, recording in 3 scenes, and 3 lightings, 4 whethers  | 2D image, Video replay, 3D Mask with materials Resin, Plaster, Silicone, Paper|\n| [WFAS](https://arxiv.org/abs/2304.05753)  | 2023 |  529,571/ 853,729 (I) | 469,920 |  Internet, unconstrained settings  | 17 PAs, Print(newspaper, poster, photo, album, picture book, scan photo, packging, cloth), Display(phone, tablet, TV, computer), Mask, 3D Model(garage kit, doll, adult doll, waxwork)|\n\n\n\u003ca name=\"data_Multimodal\" /\u003e\n\n#### Datasets with multiple modalities or specialized sensors\n\n| Dataset    | Year | #Live/Spoof | #Sub. |  M\u0026H | Setup | Attack Types |\n| --------   | -----    | -----  |  -----  | -----  | -----  |------------------------|\n| [3DMAD](https://ieeexplore.ieee.org/document/6810829)   | 2013 | 170/85(V) | 17 |  VIS, Depth | 3 sessions (2 weeks interval) | Mask(paper, hard resin)|\n| [GUC-LiFFAD](https://ieeexplore.ieee.org/document/7018027)   | 2015 | 1798/3028(V) | 80 |  Light field | Distance of 1.5 constrained conditions | Print(Inkjet paper, Laserjet paper), Replay(tablet)|\n| [3DFS-DB](https://www.researchgate.net/publication/277905873_Three-dimensional_and_two-and-a-half-dimensional_face_recognition_spoofing_using_three-dimensional_printed_models)   | 2016 | 260/260(V) | 26 |  VIS, Depth | Head movement with rich angles | Mask(plastic)|\n| [BRSU Skin/Face/Spoof](https://ieeexplore.ieee.org/document/7550052)   | 2016 | 102/404(I) | 137 |  VIS, SWIR | multispectral SWIR with 4 wavebands 935nm, 1060nm, 1300nm and 1550nm | Mask(silicon, plastic, resin, latex)|\n| [Msspoof](https://link.springer.com/chapter/10.1007/978-3-319-28501-6_8)   | 2016 | 1470/3024(I) | 21 |  VIS, NIR | 7 environmental conditions | Black\u0026white Print(flat) |\n| [MLFP](https://ieeexplore.ieee.org/document/8014774)   | 2017 | 150/1200(V) | 10 |  VIS, NIR, Thermal | Indoor and outdoor with fixed and random backgrounds | Mask(latex, paper) |\n| [ERPA](https://www.researchgate.net/publication/320177829_What_You_Can't_See_Can_Help_You_-_Extended-Range_Imaging_for_3D-Mask_Presentation_Attack_Detection)   | 2017 | Total 86(V) | 5 |  VIS, Depth, NIR, Thermal | Subject positioned close (0.3∼0.5m) to the 2 types of cameras | Print(flat), Replay(monitor), Mask(resin, silicone) |\n| [LF-SAD ](http://www.ee.cityu.edu.hk/~lmpo/publications/2019_JEI_Face_Liveness.pdf)   | 2018 | 328/596(I) | 50 |  Light field | Indoor fix background, captured by Lytro ILLUM camera | Print(flat, wrapped), Replay(monitor) |\n| [CSMAD](https://ieeexplore.ieee.org/document/8698550)   | 2018 | 104/159(V+I) | 14 |  VIS, Depth, NIR, Thermal | 4 lighting conditions | Mask(custom silicone) |\n| [3DMA](https://ieeexplore.ieee.org/document/8909845)   | 2019 | 536/384(V) | 67 |  VIS, NIR | 48 masks with different ID; 2 illumination \u0026 4 capturing distances | Mask(plastics) |\n| [CASIA-SURF](https://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_A_Dataset_and_Benchmark_for_Large-Scale_Multi-Modal_Face_Anti-Spoofing_CVPR_2019_paper.pdf)   | 2019 | 3000/18000(V) | 1000 |  VIS, Depth, NIR | Background removed; Randomly cut eyes, nose or mouth areas | Print(flat, wrapped, cut) |\n| [WMCA](https://ieeexplore.ieee.org/document/8714076)   | 2019 | 347/1332(V) | 72 |  VIS, Depth, NIR, Thermal | 6 sessions with different backgrounds and illumination; pulse data for bonafide recordings | Print(flat), Replay(tablet), Partial(glasses), Mask(plastic, silicone, and paper, Mannequin) |\n| [CeFA](https://openaccess.thecvf.com/content/WACV2021/html/Liu_CASIA-SURF_CeFA_A_Benchmark_for_Multi-Modal_Cross-Ethnicity_Face_Anti-Spoofing_WACV_2021_paper.html)   | 2020 | 6300/27900(V) | 1607 |  VIS, Depth, NIR | 3 ethnicities; outdoor \u0026 indoor; decoration with wig and glasses | Print(flat, wrapped), Replay, Mask(3D print, silica gel) |\n| [HQ-WMCA](https://ieeexplore.ieee.org/abstract/document/9146362)   | 2020 | 555/2349(V) | 51 | VIS, Depth, NIR, SWIR, Thermal | Indoor; 14 ‘modalities’, including 4 NIR and 7 SWIR wavelengths; masks and mannequins were heated up to reach body temperature | Laser or inkjet Print(flat), Replay(tablet, phone), Mask(plastic, silicon, paper, mannequin), Makeup, Partial(glasses, wigs, tatoo) |\n| [PADISI-Face](https://arxiv.org/pdf/2108.12081.pdf)   | 2021 | 1105/924(V) | 360 | VIS, Depth, NIR, SWIR, Thermal | Indoor, fixed background, 60-frame sequence of 1984 × 1264 pixel images | print(flat), replay(tablet, phone), mask(plastic, silicon, transparent, Mannequin), makeup/tatoo, partial(glasses,funny eye) |\n\n\n\n---\n\u003ca name=\"methods_RGB\" /\u003e\n\n### 2️⃣ Deep FAS methods with commercial RGB camera\n\n- temp\n\n\u003ca name=\"hybrid\" /\u003e\n\n#### Hybrid (handcrafted + deep)\n\n| Method    | Year | Backbone | Loss |  Input | Static/Dynamic |\n| --------   | -----    | -----  |  -----  | -----  | -----  |\n| [DPCNN](https://ieeexplore.ieee.org/document/7821013)   | 2016 | VGG-Face | Trained with SVM |  RGB | S|\n| [Multi-cues+NN](https://www.sciencedirect.com/science/article/pii/S1047320316300244)   | 2016 | MLP | Binary CE loss |  RGB+OFM | D|\n| [CNN LBP-TOP](https://ieeexplore.ieee.org/document/7984552)   | 2017 | 5-layer CNN | Binary CE loss, SVM |  RGB | D|\n| [DF-MSLBP](https://arxiv.org/abs/1910.03850)   | 2018 | Deep forest | Binary CE loss |  HSV+YCbCr | S|\n| [SPMT+SSD](https://www.sciencedirect.com/science/article/pii/S0031320318303182)   | 2018 | VGG16 | Binary CE loss, SVM, bbox regression |  RGB, Landmarks | S|\n| [CHIF](http://iab-rubric.org/papers/Manjani-DDLSpoofing.pdf)   | 2019 | VGG-Face | Trained with SVM |  RGB | S|\n| [DeepLBP](https://ieeexplore.ieee.org/document/8296251)   | 2019 | VGG-Face | Binary CE loss, SVM |  RGB, HSV, YCbCr | S|\n| [CNN+LBP+WLD](https://digital-library.theiet.org/content/journals/10.1049/iet-ipr.2018.5560)   | 2019 | CaffeNet | Binary CE loss |  RGB | S|\n| [Intrinsic](https://onlinelibrary.wiley.com/doi/10.1049/iet-bmt.2019.0155)   | 2019 | 1D-CNN | Trained with SVM |  Reflection | D|\n| [FARCNN](https://ieeexplore.ieee.org/document/8911314)   | 2019 | Multi-scale attentional CNN | Regression loss, Crystal loss, Center loss |  RGB | S|\n| [CNN-LSP](https://ieeexplore.ieee.org/document/8626161)   | TIFS 2019 | 1D-CNN | Trained with SVM |  RGB | D |\n| [DT-Mask](https://ieeexplore.ieee.org/document/8453011)   | 2019 | VGG16 | Binary CE loss, Channel\u0026Spatial discriminability |  RGB+OF | D |\n| [VGG+LBP](https://ieeexplore.ieee.org/document/8955089)   | 2019 | VGG16 | Binary CE loss |  RGB | S|\n| [CNN+OVLBP](http://www.mecs-press.org/ijigsp/ijigsp-v11-n2/IJIGSP-V11-N2-2.pdf)   | 2019 | VGG16 | Binary CE loss, NN classifier |  RGB | S|\n| [HOG-Pert.](https://link.springer.com/chapter/10.1007/978-3-030-20005-3_1)   | 2019 | Multi-scale CNN | Binary CE loss |  RGB+HOG | S|\n| [LBP-Pert.](https://www.sciencedirect.com/science/article/pii/S0262885619304512)   | 2020 | Multi-scale CNN | Binary CE loss |  RGB+LBP | S|\n| [TransRPPG](https://ieeexplore.ieee.org/document/9460762)   | SPL 2021 | Vision Transformer | Binary CE loss |  rPPG map | D |\n\n\n\n\u003ca name=\"binary\" /\u003e\n\n#### End-to-end binary cross-entropy supervision\n| Method    | Year | Backbone | Loss |  Input | Static/Dynamic |\n| --------   | -----    | -----  |  -----  | -----  | -----  |\n| [CNN1](https://arxiv.org/abs/1408.5601)   | 2014 | 8-layer CNN | Trained with SVM |  RGB | S|\n| [LSTM-CNN](https://ieeexplore.ieee.org/document/7486482)   | 2015 | CNN+LSTM | Binary CE loss |  RGB | D|\n| [SpoofNet](https://arxiv.org/abs/1410.1980)   | 2015 | 2-layer CNN | Binary CE loss |  RGB | S|\n| [HybridCNN](https://ieeexplore.ieee.org/document/8253209)   | 2017 | VGG-Face | Trained with SVM |  RGB | S|\n| [CNN2](https://arxiv.org/abs/1805.04176)   | 2017 | VGG11 | Binary CE loss |  RGB | S|\n| [Ultra-Deep](https://link.springer.com/chapter/10.1007/978-3-319-70096-0_70)   | 2017 | ResNet50+LSTM | Binary CE loss |  RGB | D|\n| [FASNet](https://link.springer.com/chapter/10.1007/978-3-319-59876-5_4)   | 2017 | VGG16 | Binary CE loss |  RGB | S|\n| [CNN3](https://ieeexplore.ieee.org/abstract/document/8166863)   | 2018 | Inception, ResNet | Binary CE loss |  RGB | S|\n| [MILHP](https://www.ijcai.org/proceedings/2018/0113.pdf)   | 2018 | ResNet+STN | Multiple Instances CE loss |  RGB | D|\n| [LSCNN](https://ieeexplore.ieee.org/document/8614337)   | 2018 | 9 PatchNets | Binary CE loss |  RGB | S|\n| [LiveNet](http://www.ee.cityu.edu.hk/~lmpo/publications/2018_ESA_LiveNet.pdf)   | 2018 | VGG11 | Binary CE loss |  RGB | S|\n| [MS-FANS ](https://ieeexplore.ieee.org/document/8546026)   | 2018 | AlexNet+LSTM | Binary CE loss |  RGB | S|\n| [DeepColorFAS](https://ieeexplore.ieee.org/document/8616677)   | 2018 | 5-layer CNN | Binary CE loss |  RGB, HSV, YCbCr | S|\n| [Siamese](https://link.springer.com/chapter/10.1007/978-3-030-31654-9_15)   | 2019 | AlexNet | Contrastive loss |  RGB | S|\n| [FSBuster](https://arxiv.org/abs/1902.02845)   | 2019 | ResNet50 | Trained with SVM |  RGB | S|\n| [FuseDNG](http://www.ee.cityu.edu.hk/~lmpo/publications/2019_VComm_Face_Liveness)   | 2019 | 7-layer CNN | Binary CE loss, Reconstruction loss |  RGB | S|\n| [STASN](https://openaccess.thecvf.com/content_CVPR_2019/papers/Yang_Face_Anti-Spoofing_Model_Matters_so_Does_Data_CVPR_2019_paper.pdf)   | CVPR 2019 | ResNet50+LSTM | Binary CE loss |  RGB | D|\n| [TSCNN](https://ieeexplore.ieee.org/document/8737949)   | TIFS 2019 | ResNet18 | Binary CE loss |  RGB, MSR | S|\n| [FAS-UCM](https://arxiv.org/abs/1907.07270)   | 2019 | MobileNetV2, VGG19 | Binary CE loss, Style loss |  RGB | S|\n| [SLRNN](https://bmvc2019.org/wp-content/uploads/papers/0973-paper.pdf)   | 2019 | ResNet50+LSTM | Binary CE loss |  RGB | D|\n| [GFA-CNN](https://dl.acm.org/doi/abs/10.1145/3402446)   | 2019 | VGG16 | Binary CE loss |  RGB | S|\n| [3DSynthesis](https://ieeexplore.ieee.org/document/8987415)   | 2019 | ResNet15 | Binary CE loss |  RGB | S|\n| [CompactNet](https://www.sciencedirect.com/science/article/pii/S0925231220308237?dgcid=rss_sd_all\u0026utm_source=researcher_app\u0026utm_medium=referral\u0026utm_campaign=RESR_MRKT_Researcher_inbound)   | NC 2020 | VGG19 | Points-to-Center triplet loss |  RGB | S|\n| [SSR-FCN](https://ieeexplore.ieee.org/document/9218954)   | TIFS 2020 | FCN with 6 layers | Binary CE loss |  RGB | S|\n| [FasTCo](https://arxiv.org/abs/2006.06756)   | 2020 | ResNet50 or MobileNetV2 | Multi-class CE loss, Temporal Consistency loss, Class Consistency loss|  RGB | D|\n| [DRL-FAS](https://ieeexplore.ieee.org/document/9205636)   | TIFS 2020 | ResNet18+GRU | Binary CE loss |  RGB | S|\n| [SfSNet](https://ieeexplore.ieee.org/document/9068268)   | 2020 | 6-layer CNN | Binary CE loss |  Albedo, Depth, Reflection| S|\n| [LivenesSlight](https://arxiv.org/pdf/1801.01949.pdf)   | 2020 | 6-layer CNN | Binary CE loss |  RGB | S|\n| [MotionEnhancement](https://ieeexplore.ieee.org/document/9203944)   | 2020 | VGGface+LSTM | Binary CE loss |  RGB | D|\n| [CFSA-FAS](https://ieeexplore.ieee.org/document/9175520)   | 2020 | ResNet18 | Binary CE loss |  RGB | S|\n| [MC-FBC](https://arxiv.org/abs/2005.06514)   | 2020 | VGG16, ResNet50 | Binary CE loss |  RGB | S|\n| [SimpleNet](https://arxiv.org/abs/2006.16028)   | 2020 | Multi-stream 5-layer CNN | Binary CE loss |  RGB, OF, RP | D|\n| [PatchCNN](https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0238058)   | 2020 | SqueezeNet v1.1 | Binary CE loss, Triplet loss |  RGB | S|\n| [FreqSpatialTempNet](https://arxiv.org/abs/2002.03723)   | 2020 | ResNet18 | Binary CE loss |  RGB, HSV, Spectral | D|\n| [ViTranZFAS](https://arxiv.org/abs/2011.08019)   |IJCB 2021 | ViT | Binary CE loss |  RGB | S|\n| [CIFL](https://ieeexplore.ieee.org/document/9336714)   | TIFS 2021 | ResNet18 | Binary focal loss, camear type loss |  RGB | S|\n| [XFace-PAD](https://arxiv.org/abs/2111.04862)   | FG 2021 | ResNet50, ViT | Binary CE loss, word-wise CE loss, a sentence discriminative loss, and a sentence semantic loss |  RGB | S|\n| [PCGN](https://dl.acm.org/doi/pdf/10.1145/3474085.3475305)   | MM 2021 | ResNet101+GCN | CE Loss for node and edge |  RGB whole image | S|\n| [TOD](https://arxiv.org/abs/2111.11046)   | 2021 | ResNet18, Graph Attention Network | CE Loss |  RGB  | S|\n| [MTSS](https://www.bmvc2021-virtualconference.com/assets/papers/0113.pdf)   | BMVC 2021 | ViT+Multi-Level Attention Module | CE Loss |  RGB  | S|\n| [PatchNet](https://arxiv.org/abs/2203.14325)   | CVPR 2022 | ResNet18 | Asymmetric AM-Softmax Loss, Self-Supervised Similarity Loss |  RGB patches | S|\n| [ViTransPAD](https://arxiv.org/pdf/2203.01562.pdf)   | ICIP 2022 | EfficientNet + VideoViT | CE Loss |  RGB | D|\n| [FGDNet](https://ieeexplore.ieee.org/document/9946402)   | TMM 2022 | Convolutional Transformer | 5-class CE Loss |  RGB | S|\n\n\u003ca name=\"auxiliary\" /\u003e\n\n#### Pixel-wise auxiliary supervision\n\n| Method    | Year | Supervision | Backbone |  Input | Static/Dynamic |\n| --------   | -----    | -----  |  -----  | -----  | -----  |\n| [Depth\u0026Patch](https://ieeexplore.ieee.org/document/8272713/)   | IJCB 2017 | Depth | PatchNet, DepthNet |  YCbCr, HSV | S|\n| [Auxiliary](http://cvlab.cse.msu.edu/pdfs/Liu_Jourabloo_Liu_CVPR2018.pdf)   | CVPR 2018 | Depth, rPPG spectrum | DepthNet |  RGB, HSV | D|\n| [BASN](https://openaccess.thecvf.com/content_ICCVW_2019/papers/DFW/Kim_BASN_Enriching_Feature_Representation_Using_Bipartite_Auxiliary_Supervisions_for_Face_ICCVW_2019_paper.pdf)   | ICCVW 2019 | Depth, Reflection | DepthNet, Enrichment |  RGB, HSV | S|\n| [DTN](https://openaccess.thecvf.com/content_CVPR_2019/papers/Liu_Deep_Tree_Learning_for_Zero-Shot_Face_Anti-Spoofing_CVPR_2019_paper.pdf)   | CVPR 2019 | BinaryMask | Tree Network |  RGB, HSV | S|\n| [PixBiS](http://publications.idiap.ch/downloads/papers/2019/George_ICB2019.pdf)   | ICB 2019 | BinaryMask | DenseNet161 |  RGB | S|\n| [A-PixBiS](http://www.dicta2020.org/wp-content/uploads/2020/09/53_CameraReady.pdf)   | 2020 | BinaryMask | DenseNet161 |  RGB | S|\n| [Auto-FAS](https://ieeexplore.ieee.org/document/9053587)   | ICASSP 2020 | BinaryMask | NAS |  RGB | S|\n| [MRCNN](https://www.sciencedirect.com/science/article/pii/S0167865520300015)   | 2020 | BinaryMask | Shallow CNN |  RGB | S|\n| [FCN-LSA](https://ieeexplore.ieee.org/document/9056475)   | 2020 | BinaryMask | DepthNet |  RGB | S|\n| [CDCN](https://openaccess.thecvf.com/content_CVPR_2020/papers/Yu_Searching_Central_Difference_Convolutional_Networks_for_Face_Anti-Spoofing_CVPR_2020_paper.pdf)   | CVPR 2020 | Depth | DepthNet |  RGB | S|\n| [FAS-SGTD](https://arxiv.org/abs/2003.08061)   | CVPR 2020 | Depth | DepthNet, STPM |  RGB | D|\n| [TS-FEN](https://ieeexplore.ieee.org/document/9054115)   | 2020 | Depth | ResNet34, FCN |  RGB, YCbCr, HSV | S|\n| [SAPLC](https://ieeexplore.ieee.org/document/9056824)   | 2020 | TernaryMap | DepthNet |  RGB, HSV | S|\n| [BCN](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123520545.pdf)   | ECCV 2020 | BinaryMask, Depth, Reflection | DepthNet |  RGB | S|\n| [Disentangled](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123640630.pdf)   | ECCV 2020 | Depth, TextureMap | DepthNet |  RGB | S|\n| [AENet](https://link.springer.com/chapter/10.1007/978-3-030-58610-2_5)   | ECCV 2020 | Depth, Reflection | ResNet18 |  RGB | S|\n| [3DPC-Net](https://ieeexplore.ieee.org/document/9304873)   | IJCB 2020 | 3D Point Cloud | ResNet18 |  RGB | S|\n| [PS](https://ieeexplore.ieee.org/document/9375488)   | TBIOM 2020 | BinaryMask or Depth | ResNet50 or CDCN |  RGB | S|\n| [NAS-FAS](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9252183)   | PAMI 2020 | BinaryMask or Depth | NAS |  RGB | D|\n| [DAM](https://ieeexplore.ieee.org/abstract/document/9382387)   | 2021 | Depth | VGG16, TSM |  RGB | D|\n| [Bi-FPNFAS](https://www.mdpi.com/1424-8220/21/8/2799)   | 2021 | Fourier spectra | EfficientNetB0, FPN |  RGB | S|\n| [DC-CDN](https://arxiv.org/abs/2105.01290)   | IJCAI 2021 | Depth | CDCN |  RGB | S|\n| [DCN](https://arxiv.org/pdf/2107.10628.pdf)   | IJCB 2021 | Reflection | DepthNet |  RGB | S|\n| [LMFD-PAD](https://arxiv.org/pdf/2109.07950.pdf)   | 2021 | BinaryMask | Dual-ResNet50 |  RGB + frequency map | S|\n| [MPFLN](https://openaccess.thecvf.com/content/ICCV2021W/HTCV/papers/Wang_Multi-Perspective_Features_Learning_for_Face_Anti-Spoofing_ICCVW_2021_paper.pdf)   | ICCVW 2021 | Depth, BinaryMask | CDCN, 3D-CDCN |  RGB | S, D|\n| [DSDG+DUM](https://arxiv.org/abs/2112.00568)   | TIFS 2021 | Depth | CDCN |  RGB | S|\n| [SAFPAD](https://ieeexplore.ieee.org/document/9650907)   | TIFS 2021 | Depth | DepthNet |  RGB \u0026 Patch | S|\n| [EPCR](https://arxiv.org/pdf/2111.12320.pdf)   | 2021 | BinaryMask | CDCN |  RGB | S|\n| [AISL](https://www.sciencedirect.com/science/article/pii/S0167865521004384)   | PRL 2021 | Depth | DepthNet |  RGB | S|\n| [MEGC](https://arxiv.org/abs/2202.10187)   | ICASSP 2022 | Depth, Relection, Moire, Boundary | DepthNet+Feature Enrichment |  RGB, HSV | S|\n| [EulerNet](http://ksiresearch.org/seke/seke22paper/paper076.pdf)   | 2022 | Face Location Map | EulerNet with Temporal Attention, Residual Pyramid |  RGB | D|\n| [TTN](https://ieeexplore.ieee.org/document/9730902)   | TIFS 2022 | Depth | ViT with Pyramid Temporal Aggregation, Temporal Difference Attentions |  RGB | D|\n| [TransFAS](https://ieeexplore.ieee.org/document/9817442)   | TBIOM 2022 | Depth | ViT with Cross-Layer Attentions |  RGB | S|\n| [DepthSeg](https://ieeexplore.ieee.org/document/9892826)   | IJCNN 2022 | Depth | PSPNet, DeepLabv3+ |  RGB | S|\n\n\n\u003ca name=\"generative\" /\u003e\n\n#### Generative model with pixel-wise supervision\n\n| Method    | Year | Supervision | Backbone |  Input | Static/Dynamic |\n| --------   | -----    | -----  |  -----  | -----  | -----  |\n| [De-Spoof](https://arxiv.org/abs/1807.09968)   | ECCV 2018 | Depth, BinaryMask, FourierMap | DSNet, DepthNet |  RGB, HSV | S|\n| [Reconstruction](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8997504)   | 2019 | RGB Input (live), ZeroMap (spoof) | U-Net |  RGB | S|\n| [LGSC](https://arxiv.org/abs/2005.03922)   | 2020 | ZeroMap (live) | U-Net, ResNet18 |  RGB | S|\n| [TAE](http://publications.idiap.ch/downloads/papers/2020/Mohammadi_InfoVAE_ICASSP_2020.pdf)   | ICASSP 2020 | Binary CE loss, Reconstruction loss | Info-VAE, DenseNet161 |  RGB | S|\n| [STDN](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123630392.pdf)   | ECCV 2020 | BinaryMask, RGB Input (live) | U-Net, PatchGAN |  RGB | S|\n| [GOGen](https://openaccess.thecvf.com/content_CVPR_2020/papers/Stehouwer_Noise_Modeling_Synthesis_and_Classification_for_Generic_Object_Anti-Spoofing_CVPR_2020_paper.pdf)   | CVPR 2020 | RGB input |  DepthNet |  RGB+one-hot vector | S|\n| [PhySTD](https://arxiv.org/abs/2012.05185)   | PAMI 2022 | Depth, RGB Input (live) |  U-Net, PatchGAN |  Frequency Trace | S|\n| [MT-FAS](https://ieeexplore.ieee.org/document/9462562)   | PAMI 2021 | ZeroMap (live), LearnableMap (Spoof) |  DepthNet |  RGB | S|\n| [IF-OM](https://arxiv.org/pdf/2109.04100.pdf)   | 2021 | RGB input, mixed input features |  MobileNetV2 + UNet |  RGB, mixed RGB, folded RGB | S|\n| [Dual-Stage Disentanglement](https://arxiv.org/abs/2110.09157)   | WACV 2021 | ZeroMap (live), RGB Input for reconstruction  | U-Net, ResNet18 |  RGB | S|\n\n\n\u003ca name=\"DA\" /\u003e\n\n#### Domain adaptation\n\n| Method    | Year | Backbone | Loss |  Static/Dynamic |\n| --------   | -----    | -----  |  -----  | -----  | \n| [OR-DA](https://ieeexplore.ieee.org/document/8279564)   | TIFS 2018 | AlexNet | Binary CE loss, MMD loss |  S|\n| [DTCNN](https://arxiv.org/abs/1901.05633)   | 2019 | AlexNet | Binary CE loss, MMD loss |  S|\n| [Adversarial](https://ieeexplore.ieee.org/document/8987254)   | ICB 2019 | ResNet18 | Triplet loss, Adversarial loss |  S|\n| [ML-MMD](https://ieeexplore.ieee.org/abstract/document/8795006)   | ICMEW 2019 | Multi-scale FCN | CE loss, MMD loss |  S|and unlabeled sets\n| [OCA-FAS](https://www.sciencedirect.com/science/article/pii/S0925231220313540)   | NC 2020 | DepthNet | Binary CE loss, Pixel-wise binary loss |  S|\n| [DR-UDA](https://ieeexplore.ieee.org/abstract/document/9116802)   | TIFS 2020 | ResNet18 | Center\u0026Triplet loss, Adversarial loss, Disentangled loss |  S|\n| [DGP](https://ieeexplore.ieee.org/document/9053685)   |ICASSP 2020 | DenseNet161 | Feature divergence measure, BinaryMask loss |  S|\n| [Distillation](https://signalprocessingsociety.org/publications-resources/ieee-journal-selected-topics-signal-processing/face-anti-spoofing-deep-neural)   | J-STSP 2020 | AlexNet | Binary CE loss, MMD loss , Paired Similarity |  S|\n| [SASA](https://arxiv.org/pdf/2106.14162.pdf)   | 2021 | ResNet18 | CE Loss, Adversarial loss, Less-forgetting constraints, Contrastive semantic alignment |  S|\n| [GDA](https://arxiv.org/abs/2207.10015)   |ECCV 2022 | DepthNet | CE Loss, Depth loss, Inter-domain Neural Statistic Consistency, phase consistency, Perceptual loss |  S|\n| [CDFTN](https://arxiv.org/abs/2212.03651)   |AAAI 2023 | ResNet18 | CE Loss, Reconstruction loss, triplet loss |  S|\n\n\n\n\u003ca name=\"DG\" /\u003e\n\n#### Domain generalization\n\n\n| Method    | Year | Backbone | Loss |  Static/Dynamic |\n| --------   | -----    | -----  |  -----  | -----  | \n| [MADDG](https://openaccess.thecvf.com/content_CVPR_2019/papers/Shao_Multi-Adversarial_Discriminative_Deep_Domain_Generalization_for_Face_Presentation_Attack_Detection_CVPR_2019_paper.pdf)   | CVPR 2019 | DepthNet | Binary CE \u0026 Depth loss, Multi-adversarial loss, Dual-force Triplet loss |  S|\n| [PAD-GAN](https://arxiv.org/abs/2004.01959)   | CVPR 2020 | ResNet18 | Binary CE \u0026 Depth loss, Multi-adversarial loss, Dual-force Triplet loss |  S|\n| [DASN](https://ieeexplore.ieee.org/document/9423958)   | 2020 | ResNet18 | Binary CE \u0026 Spoof-irrelevant factor loss |  S|\n| [SSDG](https://openaccess.thecvf.com/content_CVPR_2020/papers/Jia_Single-Side_Domain_Generalization_for_Face_Anti-Spoofing_CVPR_2020_paper.pdf)   | CVPR 2020  | ResNet18 | Binary CE loss, Single-Side adversarial loss, Asymmetric Triplet loss |  S|\n| [RF-Meta](https://arxiv.org/abs/1911.10771)   | AAAI 2020 | DepthNet | Binary CE loss, Depth loss |  S|\n| [CCDD](https://openaccess.thecvf.com/content_CVPRW_2020/papers/w48/Saha_Domain_Agnostic_Feature_Learning_for_Image_and_Video_Based_Face_CVPRW_2020_paper.pdf)   | CVPRW 2020 | ResNet50+LSTM | Binary CE loss, Class-conditional loss |  D|\n| [SDA](https://arxiv.org/abs/2102.12129)   |  AAAI 2021 | DepthNet | Binary CE \u0026 Depth loss, Reconstruction loss, Orthogonality regularization |  S|\n| [D2AM](https://ojs.aaai.org/index.php/AAAI/article/view/16199)   |AAAI 2021 | DepthNet | Binary CE loss, Depth loss, MMD loss |  S|\n| [DRDG](https://arxiv.org/pdf/2106.16128.pdf)   |  IJCAI 2021 | DepthNet | Binary CE loss, Depth loss, Domain loss |  S|\n| [PDL-FAS](https://arxiv.org/pdf/2107.06552.pdf)   |  2021 | DepthNet | Binary CE loss, Depth loss |  S|\n| [ANRL](https://arxiv.org/abs/2108.02667)   | ACMMM 2021 | DepthNet | Binary CE loss, Depth loss, Inter-Domain Compatible Loss, Inter-Class Separable Loss |  S|\n| [HFN+MP](https://arxiv.org/abs/2110.06753)   | 2021 | Two-stream ResNet50 | Binary CE loss, MSE loss |  S|\n| [SDFANet](https://ieeexplore.ieee.org/document/9600829)   | TIFS 2021 | ResNet-18 | BCE loss + multi-grained loss + center loss + asymmetric triplet loss  |  S|\n| [VLAD-VSA](https://dl.acm.org/doi/abs/10.1145/3474085.3475284)   | ACMMM 2021 | DepthNet or ResNet18 | BCE loss + triplet loss + domain adversarial loss + orthogonal loss +  centroid adaptation loss + intra loss  |  S|\n| [FGHV](https://arxiv.org/abs/2112.14894)   | AAAI 2022 | DepthNet | Variance + Relative Correlation + Distribution Discrimination Constraints  |  S|\n| [SSAN](https://arxiv.org/pdf/2203.05340.pdf)   | CVPR 2022 | DepthNet/ResNet18 | CE loss + Domain Adversarial loss + Contrastive loss  |  S|\n| [AMEL](https://arxiv.org/abs/2207.09868)   | ACMMM 2022 | DepthNet | CE loss, Depth loss, Feature consistency loss  |  S|\n| [MD-FAS](https://arxiv.org/pdf/2208.11148.pdf)   | ECCV 2022 | PhySTD | CE loss, Binary Mask loss, Source \u0026 Target distillation loss  |  S|\n| [FRT-PAD](https://wentianzhang-ml.github.io/pad)   | ECCV 2022 | ResNet18+GAT | CE loss  |  S|\n| [CIFAS](https://ieeexplore.ieee.org/document/9859783)   | ICME 2022 | ResNet18 | CE loss, triplet loss  |  S|\n| [OneSideTriplet](https://arxiv.org/pdf/2211.15955.pdf)   | FG 2023 | DepthNet+UNet | CE loss, triplet loss, Depth loss, Segmentation loss  |  S|\n| [DiVT](https://openaccess.thecvf.com/content/WACV2023/papers/Liao_Domain_Invariant_Vision_Transformer_Learning_for_Face_Anti-Spoofing_WACV_2023_paper.pdf)   | WACV 2023 |  MobileViT-S | Domain-invariant Concentration and Attack-separation Loss  |  S|\n| [ALDICF](https://link.springer.com/article/10.1007/s11263-023-01778-x)   | IJCV 2023 |  ResNet18, ResNet50 | Intra-domain and cross-domain discrimination loss, Conditional Domain Adversarial loss   |  S|\n| [DKG+CSA+AIAW](https://arxiv.org/abs/2304.05640)   | CVPR 2023 |  DepthNet | BCE loss, Depth loss, Asymmetric Instance Adaptive Whiting loss   |  S|\n| [SA-FAS](https://arxiv.org/abs/2303.13662)   | CVPR 2023 |  ResNet18 | Contrastive loss, Alignment loss   |  S|\n| [SPDA]([https://arxiv.org/abs/2303.13662](https://ieeexplore.ieee.org/document/10095730))   | ICASSP 2023 |  ResNet18 | BCE loss, Domain loss, Self-paced Cluster Mining loss, orthogonal loss   |  S|\n| [CRFAS]([https://arxiv.org/abs/2303.13662](https://ieeexplore.ieee.org/document/10095329))   | ICASSP 2023 |  ResNet18 | BCE loss, Domain loss,  asymmetric triplet loss, Counterfactual Feature Generation loss   |  S|\n\n\u003ca name=\"zero-shot\" /\u003e\n\n#### Zero/Few-shot learning\n\n\n| Method    | Year | Backbone | Loss |  Input |\n| --------   | -----    | -----  |  -----  | -----  | \n| [DTN](https://openaccess.thecvf.com/content_CVPR_2019/papers/Liu_Deep_Tree_Learning_for_Zero-Shot_Face_Anti-Spoofing_CVPR_2019_paper.pdf)   | CVPR 2019 | Deep Tree Network | Binary CE loss, Pixel-wise binary loss, Unsupervised Tree loss |  RGB, HSV|\n| [AIM-FAS](https://ojs.aaai.org/index.php/AAAI/article/view/6866)   | AAAI 2020 | DepthNet | Depth loss, Contrastive Depth loss |  RGB |\n| [CM-PAD](https://ieeexplore.ieee.org/document/9304920)   | IJCB 2021 | DepthNet, ResNet | Binary CE loss, Depth loss, Gradient alignment |  RGB|\n| [ViTAF](https://arxiv.org/abs/2203.12175)   | ECCV 2022 | ViT+adaptor | CE Loss,  Cosine loss |  S|\n\n\n\n\n\u003ca name=\"oneclass\" /\u003e\n\n#### Anomaly detection\n\n\n| Method    | Year | Backbone | Loss |  Input |\n| --------   | -----    | -----  |  -----  | -----  | \n| [AE+LBP](https://ieeexplore.ieee.org/abstract/document/8698574)   | 2018 | AutoEncoder | Reconstruction loss |  RGB|\n| [Anomaly](https://openaccess.thecvf.com/content_CVPRW_2019/papers/CFS/Perez-Cabo_Deep_Anomaly_Detection_for_Generalized_Face_Anti-Spoofing_CVPRW_2019_paper.pdf)   | 2019 | ResNet50 | Triplet focal loss, Metric-Softmax loss |  RGB|\n| [Anomaly2](https://ieeexplore.ieee.org/document/8682253)   | 2019 | GoogLeNet or ResNet50 | Mahalanobis distance |  RGB|\n| [Hypersphere](https://www.researchgate.net/publication/338920244_UNSEEN_FACE_PRESENTATION_ATTACK_DETECTION_WITH_HYPERSPHERE_LOSS)   | 2020 | ResNet18 | Hypersphere loss |  RGB, HSV |\n| [Ensemble-Anomaly](https://ieeexplore.ieee.org/document/9190814)   | 2020 | GoogLeNet or ResNet50 | Gaussian Mixture Model (not end-to-end) |  RGB, patches|\n| [MCCNN](https://ieeexplore.ieee.org/document/9153044)   | 2020 | LightCNN | Binary CE loss, Contrastive loss |  Grayscale, IR, Depth, Thermal|\n| [End2End-Anomaly](https://arxiv.org/abs/2007.05856)   | 2020 | VGG-Face | Binary CE loss, Pairwise confusion |  RGB|\n| [ClientAnomaly](https://www.sciencedirect.com/science/article/pii/S0031320320304994)   | PR 2020 | ResNet50 or GoogLeNet or VGG16 | One-class SVM or Mahalanobis distance or Gaussian Mixture Model |  RGB|\n| [ContrastiveEVT](https://dl.acm.org/doi/abs/10.1145/3474085.3475538)   | ACM MM 2021 | cVAE | Binary CE loss, reconstruction loss, contrastive loss|  RGB|\n| [OneClassKD](https://arxiv.org/abs/2205.03792)   | TIFS 2022 | DepthNet | Pixel-wise Binary CE loss, multi-level KD loss|  RGB|\n\n\n\u003ca name=\"semiself\" /\u003e\n\n#### Semi- \u0026 Self-supervision\n\n\n| Method    | Year | Semi/Self | Backbone | Loss |  \n| --------   | -----    | -----  |  -----  | -----  | \n| [SCNN++PL+TC](https://ieeexplore.ieee.org/document/9387164)   | TIP 2021 | Semi; Pseudo-label| ResNet18 | CE Loss |  \n| [USDAN](https://www.sciencedirect.com/science/article/pii/S0031320321000753?via%3Dihub)   | PR 2021 | Semi; Distribution Alignment| ResNet18 | Adaptive binary CE loss, Entropy loss, Adversarial loss | \n| [EPCR](https://ieeexplore.ieee.org/document/10012352)   | TIFS 2023 | Semi; Consistency Regularization | CDCN |  Prediction- \u0026 Embedding-level reconstruction loss|\n| [TSS](https://www.sciencedirect.com/science/article/pii/S0167865522000605)   | PRL 2022 | Self; Pretext task | ResNet18+BiLSTM |  CE loss for temporal sampling prediction|\n| [ACL-FAS](https://link.springer.com/chapter/10.1007/978-3-031-18910-4_39)   | PRCV 2022 | Self; Contrastive learning | - |  Region-Based Similarity Loss, Contrastive \u0026 Anti-contrastive loss|\n| [MIM-FAS](https://link.springer.com/chapter/10.1007/978-3-031-18907-4_62)   | PRCV 2022 | Self; Masked Image Modeling | ViT |  Reconstruction loss|\n| [DF-DM](https://ieeexplore.ieee.org/document/10051654)   | TNNLS 2023 | Self; Pretext task| DeepPixBiS, SSDG-R,  CDCN | GAN loss, Interpolation-based Consistency loss |\n| [MCAE](https://arxiv.org/abs/2302.08674)   | 2023 | Self+Supervised; Masked Image Modeling | ViT |  Reconstruction loss + Supervised Contrastive loss|\n| [AMA+M2A2E](https://arxiv.org/pdf/2302.05744.pdf)   | 2023 | Self; Masked Image Modeling| ViT | Reconstruction loss |\n\n\n\n\n\u003ca name=\"CL\" /\u003e\n\n#### Continual learning\n\n\n| Method    | Year | Replay or not | Backbone |  Loss |\n| --------   | -----    | -----  |  -----  | -----  | \n| [CM-PAD](https://ieeexplore.ieee.org/document/9304920)   | IJCB 2020 | with Replay | DepthNet |  batch/overall meta loss|\n| [Experience Replay](https://openaccess.thecvf.com/content/ICCV2021/papers/Rostami_Detection_and_Continual_Learning_of_Novel_Face_Presentation_Attacks_ICCV_2021_paper.pdf)   | ICCV 2021 | with Replay| ResNet50 | BCE loss for identified novel and replayed samples |  \n| [DCDCA+PPCR](https://arxiv.org/abs/2303.09914)   | 2023 | Rehearsal-Free | ViT | BCE loss, Proxy Prototype Contrastive Regularization |\n\n\n\n---\n\u003ca name=\"methods_advanced\" /\u003e\n\n### 3️⃣ Deep FAS methods with advanced sensor\n\n\n\u003ca name=\"sensor\" /\u003e\n\n#### Learning upon specialized sensor\n\n\n| Method    | Year | Backbone | Loss |  Input | Static/Dynamic |\n| --------   | -----    | -----  |  -----  | -----  | -----  |\n| [Thermal-FaceCNN](https://www.mdpi.com/2073-8994/11/3/360)   | 2019 | AlexNet | Regression loss |  Thermal infrared face image | S|\n| [SLNet](http://www.ee.cityu.edu.hk/~lmpo/publications/2019_ESA_SLNet.pdf)   | 2019 | 17-layer CNN | Binary CE loss |  Stereo (left\u0026right) face images | S|\n| [Aurora-Guard](https://arxiv.org/abs/1902.10311)   | 2019 | U-Net | Binary CE loss, Depth regression, Light Regression |  Casted face with dynamic changing light specified by random light CAPTCHA | D|\n| [LFC](http://www.ee.cityu.edu.hk/~lmpo/publications/2019_JEI_Face_Liveness.pdf)   | 2019 | AlexNet | Binary CE loss |  Ray difference/microlens images from light field camera | S|\n| [PAAS](https://dl.acm.org/doi/10.1145/3441250.3441254)   | 2020 | MobileNetV2 | Contrastive loss, SVM |  Four-directional polarized face image | S|\n| [Face-Revelio](https://dl.acm.org/doi/10.1145/3372224.3419206)   | 2020 | Siamese-AlexNet | L1 distance |  Four flash lights displayed on four quarters of a screen | D|\n| [SpecDiff](https://arxiv.org/abs/1907.12400)   | 2020 | ResNet4 | Binary CE loss |  Concatenated face images w/ and w/o flash | S|\n| [MC-PixBiS](https://arxiv.org/abs/2007.11469)   | 2020 | DenseNet161 | Binary mask loss |  SWIR images differences | S|\n| [Thermalization](https://www.mdpi.com/1424-8220/20/14/3988)   | 2020 | YOLO V3+GoogLeNet | Binary CE loss |  Thermal infrared face image | S|\n| [DP Bin-Cls-Net](https://ieeexplore.ieee.org/document/9248008)   | 2021 | Shallow U-Net + Xception | Transformation consistency, Relative disparity loss, Binary CE loss |  DP image pair | S|\n\n\n\n\n\n\u003ca name=\"multimodal\" /\u003e\n\n#### Multi-modal learning\n\n| Method    | Year | Backbone | Loss |  Input | Fusion |\n| --------   | -----    | -----  |  -----  | -----  | -----  |\n| [FaceBagNet](https://openaccess.thecvf.com/content_CVPRW_2019/html/CFS/Shen_FaceBagNet_Bag-Of-Local-Features_Model_for_Multi-Modal_Face_Anti-Spoofing_CVPRW_2019_paper.html)   | 2019 | Multi-stream CNN | Binary CE loss |  RGB, Depth, NIR face patches | Feature-level|\n| [FeatherNets](https://arxiv.org/abs/1904.09290)   | 2019 | Ensemble-FeatherNet | Binary CE loss |  Depth, NIR | Decision-level |\n| [Attention](https://openaccess.thecvf.com/content_CVPRW_2019/html/CFS/Wang_Multi-Modal_Face_Presentation_Attack_Detection_via_Spatial_and_Channel_Attentions_CVPRW_2019_paper.html)   | 2019 | ResNet18 | Binary CE loss, Center loss |  RGB, Depth, NIR | Feature-level|\n| [mmfCNN](https://dl.acm.org/doi/10.1145/3343031.3351001)   | ACMMM 2019 | ResNet34 | Binary CE loss, Binary Center Loss | RGB, NIR, Depth, HSV, YCbCr | Feature-level|\n| [MM-FAS](https://openaccess.thecvf.com/content_CVPRW_2019/papers/CFS/Parkin_Recognizing_Multi-Modal_Face_Spoofing_With_Face_Recognition_Networks_CVPRW_2019_paper.pdf)   | 2019 | ResNet18/50 | Binary CE loss |  RGB, NIR, Depth | Feature-level|\n| [AEs+MLP](https://arxiv.org/abs/1907.04048)   | 2019 | Autoencoder, MLP | Binary CE loss, Reconstruction loss |  Grayscale-Depth-Infrared composition| Input-level|\n| [SD-Net](https://ieeexplore.ieee.org/document/8995504/)   | 2019 | ResNet18 | Binary CE loss |  RGB, NIR, Depth | Feature-level|\n| [Dual-modal](https://ieeexplore.ieee.org/document/8924988)   | 2019 | MoblienetV3 | Binary CE loss |  RGB, IR | Feature-level|\n| [Parallel-CNN](https://iopscience.iop.org/article/10.1088/1742-6596/1549/4/042069)   | 2020 | Attentional CNN | Binary CE loss |  Depth, NIR | Feature-level|\n| [Multi-Channel Detector](https://arxiv.org/abs/2006.16836)   | 2020 | RetinaNet (FPN+ResNet18) | Landmark regression, Focal loss |  Grayscale-Depth-Infrared composition | Input-level|\n| [PSMM-Net](https://openaccess.thecvf.com/content/WACV2021/html/Liu_CASIA-SURF_CeFA_A_Benchmark_for_Multi-Modal_Cross-Ethnicity_Face_Anti-Spoofing_WACV_2021_paper.html)   | 2020 | ResNet18 | Binary CE loss for each stream |  RGB, Depth, NIR | Feature-level|\n| [PipeNet](https://openaccess.thecvf.com/content_CVPRW_2020/papers/w39/Yang_PipeNet_Selective_Modal_Pipeline_of_Fusion_Network_for_Multi-Modal_Face_CVPRW_2020_paper.pdf)   | 2020 | SENet154 | Binary CE loss |  RGB, Depth, NIR face patches | Feature-level|\n| [MM-CDCN](https://openaccess.thecvf.com/content_CVPRW_2020/papers/w39/Yu_Multi-Modal_Face_Anti-Spoofing_Based_on_Central_Difference_Networks_CVPRW_2020_paper.pdf)   | 2020 | CDCN | Pixel-wise binary loss, Contrastive depth loss |  RGB, Depth, NIR | Feature\u0026Decision-level|\n| [HGCNN](https://arxiv.org/abs/1811.11594)   | 2020 | Hypergraph-CNN, MLP | Binary CE loss |  RGB, Depth | Feature-level|\n| [MCT-GAN](https://link.springer.com/article/10.1007/s11042-020-08952-0)   | 2020 | CycleGAN, ResNet50 | GAN loss, Binary CE loss |  RGB, NIR | Input-level|\n| [D-M-Net](https://ieeexplore.ieee.org/document/9372969)   | 2021 | ResNeXt | Binary CE loss |  Multi-preprocessed Depth, RGB-NIR composition | Input\u0026Feature-level|\n| [MA-Net](https://ieeexplore.ieee.org/document/9374963)   | TIFS 2021 | CycleGAN, ResNet18 | Binary CE loss, GAN loss |  RGB, NIR | Feature-level|\n| [AMT](https://arxiv.org/abs/2110.09108)   | TMM 2021 | Translator: shallow encoder+decoder + ResNet; Discriminator: DenseNet | BCE loss, Pixel-wise binary loss, reconstruction loss |  illumination normalized RGB or NIR or thermal or Depth | Input-level|\n| [CompreEval](https://arxiv.org/abs/2202.10286)   | 2022 | DenseNet-161  | BCE loss, Pixel-wise binary loss |  RGB, Depth, NIR, SWIR, Thermal | Input-level|\n| [Conv-MLP](https://ieeexplore.ieee.org/document/9796574)   | TIFS 2022 | Conv-MLP | Binary CE Loss, Moat Loss |  RGB, Depth, NIR | Input-level|\n| [Echo-FAS](https://ieeexplore.ieee.org/abstract/document/9868051)   | TIFS 2022 | ResNet18, Transformer | Binary CE Loss |  RGB, Vocal | Feature-level|\n| [AMA+M2A2E](https://arxiv.org/pdf/2302.05744.pdf)   | 2023 | ViT | BCE Loss, reconstruction loss for MAE |  RGB, Depth, IR | Feature-level|\n| [SNM]([https://arxiv.org/pdf/2302.05744.pdf](https://ieeexplore.ieee.org/abstract/document/10176121))   | TIFS 2023 | ResNet18 | BCE Loss, center loss, cosine loss |  Depth, IR | Feature-level|\n\n\n\u003ca name=\"flexmodal\" /\u003e\n\n#### Flexible-modal learning\n\n| Method    | Year | Backbone | Loss |  Input | Fusion |\n| --------   | -----    | -----  |  -----  | -----  | -----  |\n| [CMFL](https://arxiv.org/abs/2103.00948)   | CVPR 2021 | DenseNet161 | Binary CE loss, Cross modal focal loss |  RGB, Depth | Feature-level|\n| [MA-ViT](https://www.ijcai.org/proceedings/2022/0165.pdf)   | IJCAI 2022 | ViT-S/16 | Binary CE Loss on image and modality |  RGB, Depth, NIR | Input\u0026Feature-level|\n| [FlexModal-FAS](https://arxiv.org/abs/2202.08192)   | CVPRW 2023 | CDCN, ResNet50, ViT | BCE loss, Pixel-wise binary loss |  RGB, Depth, IR | Feature-level|\n| [FM-ViT](https://arxiv.org/abs/2305.03277)   | TIFS 2023 | ViT | BCE loss for flexible-modal classification heads |  RGB, Depth, IR | Feature-level|\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FZitongYu%2FDeepFAS","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FZitongYu%2FDeepFAS","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FZitongYu%2FDeepFAS/lists"}