{"id":13712412,"url":"https://github.com/xiaomengyc/Few-Shot-Semantic-Segmentation-Papers","last_synced_at":"2025-05-06T22:31:11.226Z","repository":{"id":37431063,"uuid":"223518137","full_name":"xiaomengyc/Few-Shot-Semantic-Segmentation-Papers","owner":"xiaomengyc","description":"Few Shot Semantic Segmentation Papers","archived":false,"fork":false,"pushed_at":"2023-09-11T13:15:45.000Z","size":109,"stargazers_count":844,"open_issues_count":3,"forks_count":100,"subscribers_count":47,"default_branch":"master","last_synced_at":"2024-11-13T23:32:11.112Z","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/xiaomengyc.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,"governance":null}},"created_at":"2019-11-23T02:18:50.000Z","updated_at":"2024-11-12T12:43:44.000Z","dependencies_parsed_at":"2023-02-17T21:31:12.435Z","dependency_job_id":"4b2a6cb6-ef53-414f-99e6-89ea483c372d","html_url":"https://github.com/xiaomengyc/Few-Shot-Semantic-Segmentation-Papers","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/xiaomengyc%2FFew-Shot-Semantic-Segmentation-Papers","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xiaomengyc%2FFew-Shot-Semantic-Segmentation-Papers/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xiaomengyc%2FFew-Shot-Semantic-Segmentation-Papers/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xiaomengyc%2FFew-Shot-Semantic-Segmentation-Papers/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/xiaomengyc","download_url":"https://codeload.github.com/xiaomengyc/Few-Shot-Semantic-Segmentation-Papers/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252778991,"owners_count":21802862,"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":"2024-08-02T23:01:18.242Z","updated_at":"2025-05-06T22:31:10.982Z","avatar_url":"https://github.com/xiaomengyc.png","language":null,"funding_links":[],"categories":["Table of Contents","Few-Shot Segmentation"],"sub_categories":[],"readme":"# Few Shot Semantic Segmentation Papers [![Awesome](https://awesome.re/badge.svg)](https://awesome.re)\n\n*NOTE:* If your paper is not in the list, plese feel free to [raise an issue](https://github.com/xiaomengyc/Few-Shot-Semantic-Segmentation-Papers/issues) or drop me an [e-mail](mailto:solli.zhang@gmail.com?subject=[GitHub]%fewshot%papers).\n\n## 2023\n| Title | Venue | PDF | CODE |\n| :-----|:-----:|:---:|:----:|\n| A Strong Baseline for Generalized Few-Shot Semantic Segmentation | CVPR | [PDF](https://arxiv.org/abs/2211.14126) | [CODE](https://github.com/sinahmr/DIaM)|\n| Few Shot Semantic Segmentation: a review of methodologies and open challenges | arXiv | [PDF](https://arxiv.org/pdf/2304.05832.pdf) | - |\n| Elimination of Non-Novel Segments at Multi-Scale for Few-Shot Segmentation | WACV | [PDF](https://arxiv.org/abs/2211.02300) | - |\n\n\n## 2022\n| Title | Venue | PDF | CODE |\n| :-----|:-----:|:---:|:----:|\n| Few-shot Medical Image Segmentation with Cycle-resemblance Attention | WACV | [PDF](https://arxiv.org/pdf/2212.03967.pdf) | - |\n| Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning | NeurIPS | [PDF](https://arxiv.org/pdf/2206.06122.pdf) | [CODE](https://github.com/syp2ysy/SVF) |\n| Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation | ECCV | [PDF](https://arxiv.org/pdf/2207.10866.pdf) | [CODE](https://seokju-cho.github.io/VAT/) |\n| Cross-Domain Few-Shot Semantic Segmentation | ECCV | [PDF](https://slei109.github.io/papers/eccv-cdfss.pdf) | [CODE](https://github.com/slei109/PATNet) |\n| Self-Support Few-Shot Semantic Segmentation | ECCV | [PDF](https://arxiv.org/pdf/2207.11549.pdf) | [CODE](https://github.com/fanq15/SSP) |\n| Interclass Prototype Relation for Few-Shot Segmentation | ECCV | [PDF](https://arxiv.org/pdf/2211.08681.pdf) | [CODE](http://fss-stat.s3-website-us-east-1.amazonaws.com/IPRNet.zip) |\n| Generalized Few-shot Semantic Segmentation | CVPR | [PDF](https://jiaya.me/papers/cvpr22_zhuotao.pdf) | [CODE](https://github.com/dvlab-research/GFS-Seg)\n| Integrative Few-Shot Learning for Classification and Segmentation | CVPR | [PDF](https://arxiv.org/abs/2203.15712) | [CODE](https://github.com/dahyun-kang/ifsl) |\n| Learning What Not to Segment: A New Perspective on Few-Shot Segmentation | CVPR | [PDF](https://arxiv.org/abs/2203.07615) | [CODE](https://github.com/chunbolang/BAM) |\n| APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation | TMM | [PDF](https://ieeexplore.ieee.org/document/9773019) | - |\n| MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation | arXiv | [PDF](https://arxiv.org/pdf/2206.09667.pdf) | [CODE](https://github.com/AIVResearch/MSANet) |\n\n\n## 2021\n| Title | Venue | PDF | CODE |\n| :-----|:-----:|:---:|:----:|\n| Few-shot Semantic Segmentation with Self-supervision from Pseudo-classes | BMVC | [PDF](https://www.bmvc2021-virtualconference.com/assets/papers/0595.pdf) | [CODE](https://github.com/kate-sann5100/SS_few_shot) |\n| Rich Embedding Features for One-Shot Semantic Segmentation | TNNLS | [PDF](https://ieeexplore.ieee.org/abstract/document/9463398) | - |\n| Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer| ICCV | [PDF](https://arxiv.org/pdf/2108.03032.pdf) | [CODE](https://github.com/zhiheLu/CWT-for-FSS) |\n| Hypercorrelation Squeeze for Few-Shot Segmentation | ICCV | [PDF](https://arxiv.org/pdf/2104.01538.pdf) | [CODE](https://github.com/juhongm999/hsnet) |\n| Mining Latent Classes for Few-shot Segmentation | ICCV | [PDF](https://arxiv.org/pdf/2103.15402.pdf) | [CODE](https://github.com/LiheYoung/MiningFSS) |\n| Few-Shot Semantic Segmentation with Cyclic Memory Network | ICCV | [PDF](https://openaccess.thecvf.com/content/ICCV2021/papers/Xie_Few-Shot_Semantic_Segmentation_With_Cyclic_Memory_Network_ICCV_2021_paper.pdf) | - |\n| Learning Meta-class Memory for Few-Shot Semantic Segmentation | ICCV | [PDF](https://openaccess.thecvf.com/content/ICCV2021/papers/Wu_Learning_Meta-Class_Memory_for_Few-Shot_Semantic_Segmentation_ICCV_2021_paper.pdf) | [CODE](https://github.com/wu-zhonghua/MM-Net) |\n| Progressive One-Shot Human Parsing | AAAI | [PDF](https://arxiv.org/pdf/2012.11810.pdf) | [CODE](https://github.com/Charleshhy/One-shot-Human-Parsing) |\n| Bidirectional RNN-based Few Shot Learning for 3D Medical Image Segmentation | AAAI | [PDF](https://ojs.aaai.org/index.php/AAAI/article/view/16275) | [CODE](https://github.com/oopil/3D_medical_image_FSS) |\n| Scale-Aware Graph Neural Network for Few-Shot Semantic Segmentation | CVPR | [PDF](https://openaccess.thecvf.com/content/CVPR2021/papers/Xie_Scale-Aware_Graph_Neural_Network_for_Few-Shot_Semantic_Segmentation_CVPR_2021_paper.pdf) | - |\n| Adaptive Prototype Learning and Allocation for Few-Shot Segmentation | CVPR | [PDF](https://arxiv.org/pdf/2104.01893.pdf) | [CODE](https://github.com/Reagan1311/ASGNet) |\n| Self-Guided and Cross-Guided Learning for Few-Shot Segmentation | CVPR | [PDF](https://arxiv.org/pdf/2103.16129.pdf) | [CODE](https://github.com/zbf1991/SCL) |\n| Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need? | CVPR  | [PDF](https://arxiv.org/pdf/2012.06166.pdf) | [CODE](https://github.com/mboudiaf/RePRI-for-Few-Shot-Segmentation) |\n| On the Texture Bias for Few-Shot CNN Segmentation | WACV | [PDF](https://arxiv.org/pdf/2003.04052v1.pdf) | [CODE](https://github.com/rezazad68/fewshot-segmentation) |\n| A Location-Sensitive Local Prototype Network for Few-Shot Medical Image Segmentation | ISBI | [PDF](https://arxiv.org/pdf/2103.10178.pdf) | - |\n| Dense Gaussian Processes for Few-Shot Segmentation | arXiv | [PDF](https://arxiv.org/pdf/2110.03674.pdf) | - |\n| End-to-end One-shot Human Parsing | arXiv | [PDF](https://arxiv.org/pdf/2105.01241.pdf) | - |\n| Few-Shot Segmentation with Global and Local Contrastive Learning | arXiv | [PDF](https://arxiv.org/pdf/2108.05293.pdf) | - |\n| Few-shot Segmentation with Optimal Transport Matching and Message Flow | arXiv | [PDF](https://arxiv.org/pdf/2108.08518.pdf) | - |\n| Uncertainty-Aware Semi-Supervised Few Shot Segmentation | arXiv | [PDF](https://arxiv.org/pdf/2110.08954.pdf) | - |\n\n\n## 2020\n| Title | Venue | PDF | CODE |\n| :-----|:-----:|:---:|:----:|\n| Prior Guided Feature Enrichment Network for Few-Shot Segmentation | TPAMI | [PDF](https://arxiv.org/abs/2008.01449) | [CODE](https://github.com/dvlab-research/PFENet) |\n| Dynamic Extension Nets for Few-shot Semantic Segmentation | MM | [PDF](https://dl.acm.org/doi/abs/10.1145/3394171.3413915) | [CODE](https://github.com/lizhaoliu-Lec/DENet) |\n| Semi-supervised few-shot learning for medical image segmentation | arXiv | [PDF](https://arxiv.org/pdf/2003.08462.pdf) | [CODE](https://github.com/fayjie92/FSMS-Surrogate) |\n| Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need? | arXiv | [PDF](https://arxiv.org/pdf/2012.06166.pdf) | [CODE](https://github.com/mboudiaf/RePRI-for-Few-Shot-Segmentation) |\n| Meta-Learning Initializations for Image Segmentation | NeurIPS-W | [PDF](https://meta-learn.github.io/2020/papers/44_paper.pdf) | [CODE](https://github.com/ml4ai/mliis) |\n| BriNet: Towards Bridging the Intra-class and Inter-class Gaps in One-Shot Segmentation | arXiv |[PDF](https://arxiv.org/pdf/2008.06226.pdf) | [CODE](https://github.com/Wi-sc/BriNet) |\n| Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation | ECCV | [PDF](https://arxiv.org/pdf/2007.09886v2.pdf) | [CODE](https://github.com/cheng-01037/Self-supervised-Fewshot-Medical-Image-Segmentation) |\n| Generalized Few-Shot Semantic Segmentation | arXiv | [PDF](https://arxiv.org/pdf/2010.05210.pdf) | - |\n| FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation | CVPR | [PDF](https://openaccess.thecvf.com/content_CVPR_2020/papers/Li_FSS-1000_A_1000-Class_Dataset_for_Few-Shot_Segmentation_CVPR_2020_paper.pdf) | [CODE](https://github.com/HKUSTCV/FSS-1000) |\n| Few-Shot Semantic Segmentation with Democratic Attention Networks | ECCV | [PDF](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123580715.pdf) | - |\n| Prototype Mixture Models for Few-shot Semantic Segmentation | ECCV | [PDF](https://arxiv.org/pdf/2008.03898.pdf) | [CODE](https://github.com/Yang-Bob/PMMs) |\n|  PFENet: Prior Guided Feature Enrichment Network for Few-shot Segmentation| TPAMI | [PDF](https://arxiv.org/pdf/2008.01449.pdf) | [CODE](https://github.com/Jia-Research-Lab/PFENet) |\n| Part-aware Prototype Network for Few-shot Semantic Segmentation | ECCV | [PDF](https://arxiv.org/pdf/2007.06309.pdf) | [CODE](https://github.com/Xiangyi1996/PPNet-PyTorch) |\n| SimPropNet: Improved Similarity Propagation for Few-shot Image Segmentation | IJCAI | [PDF](https://arxiv.org/pdf/2004.15014.pdf) | - |\n| Objectness-Aware One-Shot Semantic Segmentation | arXiv | [PDF](https://arxiv.org/pdf/2004.02945.pdf) | - |\n| Self-Supervised Tuning for Few-Shot Segmentation | arXiv | [PDF](https://arxiv.org/pdf/2004.05538.pdf) | - |\n| SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation | TCYB | [PDF](https://arxiv.org/abs/1810.09091) | [CODE](https://github.com/xiaomengyc/SG-One)|\n| CAFENet: Class-Agnostic Few-Shot Edge Detection Network | arXiv | [PDF](https://arxiv.org/pdf/2003.08235.pdf) | - |\n| FGN: Fully Guided Network for Few-Shot Instance Segmentation | CVPR | [PDF](https://arxiv.org/pdf/2003.13954.pdf) | - |\n| CRNet: Cross-Reference Networks for Few-Shot Segmentation | CVPR | [PDF](https://arxiv.org/pdf/2003.10658.pdf) | - |\n| Differentiable Meta-learning Model for Few-shot Semantic Segmentation | AAAI | [PDF](https://arxiv.org/pdf/1911.10371.pdf) | - |\n| Prototype Refinement Network for Few-Shot Segmentation | arXiv | [PDF](https://arxiv.org/pdf/2002.03579.pdf) | - |\n| Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Embeddings | IJCAI | [PDF](https://www.ijcai.org/Proceedings/2020/0120.pdf) | - |\n\n\n## 2019\n| Title | Venue | PDF | CODE |\n| :-----|:-----:|:---:|:----:|\n|Attention-Based Multi-Context Guiding for Few-Shot Semantic Segmentation|AAAI|[PDF](https://ojs.aaai.org/index.php/AAAI/article/view/4860)|[CODE](https://github.com/dongzhuoyao/tensorpack/tree/deeplab/examples/one-shot-seg)|\n| A deep one-shot network for query-based logo retrieval | PR | [PDF](https://arxiv.org/pdf/1811.01395.pdf) |-|\n| PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment | ICCV | [PDF](http://openaccess.thecvf.com/content_ICCV_2019/papers/Wang_PANet_Few-Shot_Image_Semantic_Segmentation_With_Prototype_Alignment_ICCV_2019_paper.pdf) | [CODE](https://github.com/kaixin96/PANet) |\n| Pyramid Graph Networks with Connection Attentions for Region-Based One-Shot Semantic Segmentation | ICCV | [PDF](http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhang_Pyramid_Graph_Networks_With_Connection_Attentions_for_Region-Based_One-Shot_Semantic_ICCV_2019_paper.pdf)| - |\n| AMP: Adaptive Masked Proxies for Few-Shot Segmentation | ICCV | [PDF](http://openaccess.thecvf.com/content_ICCV_2019/papers/Siam_AMP_Adaptive_Masked_Proxies_for_Few-Shot_Segmentation_ICCV_2019_paper.pdf) | [CODE](https://github.com/MSiam/AdaptiveMaskedProxies) |\n| Feature Weighting and Boosting for Few-Shot Segmentation |  ICCV | [PDF](http://openaccess.thecvf.com/content_ICCV_2019/papers/Nguyen_Feature_Weighting_and_Boosting_for_Few-Shot_Segmentation_ICCV_2019_paper.pdf) | - |\n| CANet: Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot Learning | CVPR | [PDF](http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_CANet_Class-Agnostic_Segmentation_Networks_With_Iterative_Refinement_and_Attentive_Few-Shot_CVPR_2019_paper.pdf) | [CODE](https://github.com/icoz69/CaNet) |\n| Adaptive Masked Weight Imprinting for Few-Shot Segmentation | ICLRW | [PDF](https://openreview.net/pdf?id=SkeoV4yZUV) | - |\n| A New Local Transformation Module for Few-Shot Segmentation | MMMM | [PDF](https://link.springer.com/chapter/10.1007/978-3-030-37734-2_7) |\n| A New Few-shot Segmentation Network Based on Class Representation | arXiv | [PDF](https://arxiv.org/pdf/1909.08754.pdf) |\n\n## 2018\n| Title | Venue | PDF | CODE |\n| :-----|:-----:|:---:|:----:|\n| Conditional networks for few-shot semantic segmentation | ICLRW | [PDF](https://openreview.net/pdf?id=SkMjFKJwG) |  [CODE](https://github.com/shelhamer/revolver)  |\n| Few-Shot Semantic Segmentation with Prototype Learning | BMVC | [PDF](http://bmvc2018.org/contents/papers/0255.pdf) | - |\n\n## 2017\n| Title | Venue | PDF | CODE |\n| :-----|:-----:|:---:|:----:|\n| One-Shot Learning for Semantic Segmentation | BMVC | [PDF](https://arxiv.org/abs/1709.03410) | [CODE](https://github.com/lzzcd001/OSLSM) |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxiaomengyc%2FFew-Shot-Semantic-Segmentation-Papers","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fxiaomengyc%2FFew-Shot-Semantic-Segmentation-Papers","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxiaomengyc%2FFew-Shot-Semantic-Segmentation-Papers/lists"}