Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.
Awesome Lists | Featured Topics | Projects
https://github.com/lxn96/awesome-few-shot-object-detection

Collect some papers and datastes about few-shot object detection for computer vision.
https://github.com/lxn96/awesome-few-shot-object-detection
List: awesome-few-shot-object-detection
Last synced: 3 months ago
JSON representation
Collect some papers and datastes about few-shot object detection for computer vision.
Host: GitHub
URL: https://github.com/lxn96/awesome-few-shot-object-detection
Owner: lxn96
Created: 2022-04-10T08:34:25.000Z (over 2 years ago)
Default Branch: main
Last Pushed: 2023-09-26T16:27:35.000Z (about 1 year ago)
Last Synced: 2024-05-21T20:08:17.456Z (6 months ago)
Size: 59.6 KB
Stars: 122
Watchers: 5
Forks: 14
Open Issues: 0
Metadata Files:
- Readme: README.md
Awesome Lists containing this project

ultimate-awesome - awesome-few-shot-object-detection - Collect some papers and datastes about few-shot object detection for computer vision. (Other Lists / PowerShell Lists)
README

        # Awesome-Few-Shot-Object-Detection

Collect some papers about few-shot object detection for computer vision. Additionally, we briefly introduce the commonly used datasets for few-shot object detection.

##  Papers

### Survey

| Title | Venue | PDF |

| :-----|:-----:|:-----:|

| A Survey of Deep Learning for Low-Shot Object Detection | ArXiv 2022 | [PDF](https://arxiv.org/pdf/2112.02814.pdf) |

| A Unified Framework for Attention-Based Few-Shot Object Detection | ArXiv 2022 | [PDF](https://arxiv.org/pdf/2201.02052.pdf) |

### 2023

| Title | Venue | Dataset | PDF | CODE |

| :-----|:-----:|:---:|:---:|:----:|

| FS-DETR: Few-Shot DEtection TRansformer with prompting and without re-training | ICCV 2023 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/ICCV2023/papers/Bulat_FS-DETR_Few-Shot_DEtection_TRansformer_with_Prompting_and_without_Re-Training_ICCV_2023_paper.pdf) | - |

| σ-Adaptive Decoupled Prototype for Few-Shot Object Detection | ICCV 2023 | PASCAL VOC & MS COCO & FSOD | [PDF](https://openaccess.thecvf.com/content/ICCV2023/papers/Du_s-Adaptive_Decoupled_Prototype_for_Few-Shot_Object_Detection_ICCV_2023_paper.pdf) | - |

| Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection | CVPR 2023 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_Generating_Features_With_Increased_Crop-Related_Diversity_for_Few-Shot_Object_Detection_CVPR_2023_paper.pdf) | - |

| Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detection | CVPR 2023 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/CVPR2023/papers/Demirel_Meta-Tuning_Loss_Functions_and_Data_Augmentation_for_Few-Shot_Object_Detection_CVPR_2023_paper.pdf) | - |

| NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forging | CVPR 2023 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/CVPR2023/papers/Guirguis_NIFF_Alleviating_Forgetting_in_Generalized_Few-Shot_Object_Detection_via_Neural_CVPR_2023_paper.pdf) | - |

| DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection | CVPR 2023 | PASCAL VOC & MS COCO & LVIS | [PDF](https://openaccess.thecvf.com/content/CVPR2023/papers/Ma_DiGeo_Discriminative_Geometry-Aware_Learning_for_Generalized_Few-Shot_Object_Detection_CVPR_2023_paper.pdf) | - |

| Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detection | AAAI 2023 | PASCAL VOC & MS COCO | [PDF](https://arxiv.org/pdf/2211.14782.pdf) | [CODE](https://github.com/lxn96/ICPE) |

| Few-Shot Object Detection via Variational Feature Aggregation | AAAI 2023 |  PASCAL VOC & MS COCO | [PDF](https://arxiv.org/pdf/2301.13411.pdf) | [CODE](https://github.com/csuhan/VFA) |

| Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from A Conditional Causal Perspective | AAAI 2023 | PASCAL VOC & MS COCO | [PDF](https://arxiv.org/pdf/2208.12681.pdf) | [CODE](https://github.com/ZYN-1101/DandR.git) |

### 2022

| Title | Venue | Dataset | PDF | CODE |

| :-----|:-----:|:---:|:---:|:----:|

| Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark | ECCV 2022 | LVIS & MS COCO | [PDF](https://arxiv.org/pdf/2207.11169.pdf) | - |

| AirDet: Few-Shot Detection without Fine-Tuning for Autonomous Exploration | ECCV 2022 | PASCAL VOC & MS COCO | [PDF](https://arxiv.org/pdf/2112.01740.pdf) | [CODE](https://github.com/Jaraxxus-Me/AirDet) |

| Less than Few: Self-Shot Video Instance Segmentation | ECCV 2022 | MS COCO | [PDF](https://arxiv.org/pdf/2204.08874.pdf) | - |

| Time-rEversed diffusioN tEnsor Transformer: A New TENET of Few-Shot Object Detection | ECCV 2022 | PASCAL VOC & MS COCO & FSOD | [PDF](https://arxiv.org/pdf/2210.16897.pdf) | [CODE](https://github.com/ZS123-lang/TENET) |

| VizWiz-FewShot: Locating Objects in Images Taken by People with Visual Impairments | ECCV 2022 | PASCAL VOC & MS COCO | [PDF](https://arxiv.org/pdf/2207.11810.pdf) | [CODE](https://vizwiz.org/) |

| Multi-faceted Distillation of Base-Novel Commonality for Few-Shot Object Detection | ECCV 2022 | PASCAL VOC & MS COCO | [PDF](https://arxiv.org/pdf/2207.11184.pdf) | [CODE](https://github.com/WuShuang1998/MFDC) |

| Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations | ECCV 2022 | PASCAL VOC & MS COCO | [PDF](https://arxiv.org/pdf/2207.12049.pdf) | - |

| Few-Shot Object Detection with Model Calibration | ECCV 2022 | PASCAL VOC & MS COCO | [PDF](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136790707.pdf) | [CODE](https://github.com/fanq15/FewX) |

| Few-Shot Video Object Detectio | ECCV 2022 | FSVOD-500 | [PDF](https://arxiv.org/pdf/2104.14805.pdf) | [CODE](https://github.com/fanq15/FewX) |

| Few-Shot Object Counting and Detection | ECCV 2022 | FSCD-147 & FSCD-LVIS | [PDF](https://arxiv.org/pdf/2207.10988.pdf) | [CODE](https://github.com/VinAIResearch/Counting-DETR) |

| Mutually Reinforcing Structure with Proposal Contrastive Consistency for Few-Shot Object Detection | ECCV 2022 | PASCAL VOC & MS COCO | [PDF](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136800388.pdf) | [CODE](https://github.com/MMatx/MRSN) |

| Few-Shot End-to-End Object Detection via Constantly Concentrated Encoding across Heads | ECCV 2022 | PASCAL VOC & MS COCO | [PDF](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136860056.pdf) | - |

| AcroFOD: An Adaptive Method for Cross-Domain Few-Shot Object Detection | ECCV 2022 | Cityscapes & SIM10k | [PDF](https://arxiv.org/pdf/2207.11169.pdf) | [CODE](https://github.com/Hlings/AcroFOD) |

| Kernelized Few-shot Object Detection with Efficient Integral Aggregation | CVPR 2022 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/CVPR2022/papers/Zhang_Kernelized_Few-Shot_Object_Detection_With_Efficient_Integral_Aggregation_CVPR_2022_paper.pdf) | [CODE](https://github.com/ZS123-lang/KFSOD) |

| Label, Verify, Correct: A Simple Few Shot Object Detection Method | CVPR 2022 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/CVPR2022/papers/Kaul_Label_Verify_Correct_A_Simple_Few_Shot_Object_Detection_Method_CVPR_2022_paper.pdf) | [CODE](https://github.com/prannaykaul/lvc) |

| Few-Shot Object Detection with Fully Cross-Transformer | CVPR 2022 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/CVPR2022/papers/Han_Few-Shot_Object_Detection_With_Fully_Cross-Transformer_CVPR_2022_paper.pdf) | - |

| Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment | AAAI 2022 | PASCAL VOC & MS COCO | [PDF](https://arxiv.org/pdf/2104.07719.pdf) | [CODE](https://github.com/GuangxingHan/Meta-Faster-R-CNN) |

| Few-Shot Object Detection by Attending to Per-Sample-Prototype | WACV 2022 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/WACV2022/papers/Lee_Few-Shot_Object_Detection_by_Attending_to_Per-Sample-Prototype_WACV_2022_paper.pdf) | - |

### 2021

| Title | Venue | Dataset | PDF | CODE |

| :-----|:-----:|:---:|:---:|:----:|

| Generalized and Discriminative Few-Shot Object Detection via SVD-Dictionary Enhancement | NeurIPS 2021 | PASCAL VOC & MS COCO | [PDF](https://proceedings.neurips.cc/paper/2021/hash/325995af77a0e8b06d1204a171010b3a-Abstract.html) | [CODE](https://github.com/AmingWu/SVD-Dictionary-Enhancement) |

| Few-Shot Object Detection via Association and DIscrimination | NeurIPS 2021 | PASCAL VOC & MS COCO | [PDF](https://proceedings.neurips.cc/paper/2021/hash/8a1e808b55fde9455cb3d8857ed88389-Abstract.html) | [CODE](https://github.com/yhcao6/FADI) |

| Adaptive Image Transformer for One-Shot Object Detection | CVPR 2021 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/CVPR2021/papers/Chen_Adaptive_Image_Transformer_for_One-Shot_Object_Detection_CVPR_2021_paper.pdf) | [CODE](https://github.com/WOMMOW/AIT) |

| Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection | CVPR 2021 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/CVPR2021/papers/Hu_Dense_Relation_Distillation_With_Context-Aware_Aggregation_for_Few-Shot_Object_Detection_CVPR_2021_paper.pdf) | [CODE](https://github.com/hzhupku/DCNet) |

| Generalized Few-Shot Object Detection without Forgetting | CVPR 2021 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/CVPR2021/papers/Fan_Generalized_Few-Shot_Object_Detection_Without_Forgetting_CVPR_2021_paper.pdf) | [CODE](https://github.com/Megvii-BaseDetection/GFSD) |

| Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection | CVPR 2021 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/CVPR2021/papers/Li_Beyond_Max-Margin_Class_Margin_Equilibrium_for_Few-Shot_Object_Detection_CVPR_2021_paper.pdf) | [CODE](https://github.com/Bohao-Lee/CME) |

| Few-Shot Object Detection via Classification Refinement and Distractor Retreatment | CVPR 2021 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/CVPR2021/papers/Li_Few-Shot_Object_Detection_via_Classification_Refinement_and_Distractor_Retreatment_CVPR_2021_paper.pdf) | - |

| Transformation Invariant Few-Shot Object Detection | CVPR 2021 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/CVPR2021/papers/Li_Transformation_Invariant_Few-Shot_Object_Detection_CVPR_2021_paper.pdf) | - |

| UniT: Unified Knowledge Transfer for Any-shot Object Detection and Segmentation | CVPR 2021 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/CVPR2021/papers/Khandelwal_UniT_Unified_Knowledge_Transfer_for_Any-Shot_Object_Detection_and_Segmentation_CVPR_2021_paper.pdf) | [CODE](https://github.com/ubc-vision/UniT) |

| FAPIS: A Few-shot Anchor-free Part-based Instance Segmenter | CVPR 2021 | MS COCO | [PDF](https://openaccess.thecvf.com/content/CVPR2021/papers/Nguyen_FAPIS_A_Few-Shot_Anchor-Free_Part-Based_Instance_Segmenter_CVPR_2021_paper.pdf) | [CODE](https://github.com/ducminhkhoi/FAPIS) |

| Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection | CVPR 2021 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/CVPR2021/papers/Zhu_Semantic_Relation_Reasoning_for_Shot-Stable_Few-Shot_Object_Detection_CVPR_2021_paper.pdf) | - |

| FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding | CVPR 2021 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/CVPR2021/papers/Sun_FSCE_Few-Shot_Object_Detection_via_Contrastive_Proposal_Encoding_CVPR_2021_paper.pdf) | [CODE](https://github.com/MegviiDetection/FSCE) |

| Accurate Few-shot Object Detection with Support-Query Mutual Guidance and Hybrid Loss | CVPR 2021 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/CVPR2021/papers/Zhang_Accurate_Few-Shot_Object_Detection_With_Support-Query_Mutual_Guidance_and_Hybrid_CVPR_2021_paper.pdf) | - |

| Hallucination Improves Few-Shot Object Detection | CVPR 2021 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/CVPR2021/papers/Zhang_Hallucination_Improves_Few-Shot_Object_Detection_CVPR_2021_paper.pdf) | [CODE](https://github.com/pppplin/HallucFsDet) |

| Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networks | ICCV 2021 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/ICCV2021/papers/Han_Query_Adaptive_Few-Shot_Object_Detection_With_Heterogeneous_Graph_Convolutional_Networks_ICCV_2021_paper.pdf) | [CODE](https://github.com/GuangxingHan/QA-FewDet) |

| Universal-Prototype Enhancing for Few-Shot Object Detection | ICCV 2021 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/ICCV2021/papers/Wu_Universal-Prototype_Enhancing_for_Few-Shot_Object_Detection_ICCV_2021_paper.pdf) | [CODE](https://github.com/AmingWu/UP-FSOD) |

| DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection | ICCV 2021 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content/ICCV2021/papers/Qiao_DeFRCN_Decoupled_Faster_R-CNN_for_Few-Shot_Object_Detection_ICCV_2021_paper.pdf) | [CODE](https://github.com/er-muyue/DeFRCN) |

| Meta-DETR: Few-Shot Object Detection via Unified Image-Level Meta-Learning | ArXiv 2021 | PASCAL VOC & MS COCO | [PDF](https://arxiv.org/pdf/2103.11731v2.pdf) | [CODE](https://github.com/ZhangGongjie/Meta-DETR) |

### 2020

| Title | Venue | Dataset | PDF | CODE |

| :-----|:-----:|:---:|:---:|:----:|

| Restoring Negative Information in Few-Shot Object Detection | NeurIPS 2020 | PASCAL VOC & ImageNet-LOC | [PDF](https://proceedings.neurips.cc/paper/2020/hash/240ac9371ec2671ae99847c3ae2e6384-Abstract.html) | [CODE](https://github.com/yang-yk/NP-RepMet) |

| Context-Transformer: Tackling Object Confusion for Few-Shot Detection | AAAI 2020 | PASCAL VOC & MS COCO | [PDF](https://ojs.aaai.org/index.php/AAAI/article/download/6957/6811) | [CODE](https://github.com/Ze-Yang/Context-Transformer) |

| Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector | CVPR 2020 | MS COCO & ImageNet-LOC | [PDF](https://openaccess.thecvf.com/content_CVPR_2020/papers/Fan_Few-Shot_Object_Detection_With_Attention-RPN_and_Multi-Relation_Detector_CVPR_2020_paper.pdf) | [CODE](https://github.com/fanq15/FSOD-code) |

| Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild | ECCV 2020 | PASCAL VOC & MS COCO | [PDF](https://arxiv.org/pdf/2007.12107.pdf) | [CODE](http://imagine.enpc.fr/~xiaoy/FSDetView/) |

| Multi-Scale Positive Sample Refinement for Few-Shot Object Detection | ECCV 2020 | PASCAL VOC & MS COCO | [PDF](https://arxiv.org/pdf/2007.09384.pdf?ref=https://githubhelp.com) | [CODE](https://github.com/jiaxi-wu/MPSR) |

| META-RCNN: META LEARNING FOR FEW-SHOT OBJECT DETECTION | ICLR 2020 | PASCAL VOC & ImageNet-LOC | [PDF](https://openreview.net/pdf?id=B1xmOgrFPS) | - |

| Frustratingly Simple Few-Shot Object Detection | ICML 2020 | PASCAL VOC & MS COCO & LVIS | [PDF](https://arxiv.org/pdf/2003.06957.pdf?ref=https://githubhelp.com) | [CODE](https://github.com/ucbdrive/few-shot-object-detection) |

### 2019

| Title | Venue | Dataset | PDF | CODE |

| :-----|:-----:|:---:|:---:|:----:|

| Few-shot Object Detection via Feature Reweighting | ICCV 2019 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content_ICCV_2019/papers/Kang_Few-Shot_Object_Detection_via_Feature_Reweighting_ICCV_2019_paper.pdf) | [CODE](https://github.com/bingykang/Fewshot_Detection) |

| RepMet: Representative-based metric learning for classification and few-shot object detection | CVPR 2019 | PASCAL VOC & ImageNet-LOC | [PDF](https://openaccess.thecvf.com/content_CVPR_2019/papers/Karlinsky_RepMet_Representative-Based_Metric_Learning_for_Classification_and_Few-Shot_Object_Detection_CVPR_2019_paper.pdf) | [CODE](https://github.com/jshtok/RepMet) |

| Meta R-CNN : Towards General Solver for Instance-level Low-shot Learning | ICCV 2019 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content_ICCV_2019/papers/Yan_Meta_R-CNN_Towards_General_Solver_for_Instance-Level_Low-Shot_Learning_ICCV_2019_paper.pdf) | [CODE](https://github.com/yanxp/MetaR-CNN) |

| MetaDet: Meta-Learning to Detect Rare Objects | ICCV 2019 | PASCAL VOC & MS COCO | [PDF](https://openaccess.thecvf.com/content_ICCV_2019/papers/Wang_Meta-Learning_to_Detect_Rare_Objects_ICCV_2019_paper.pdf) | - |

| One-Shot Object Detection with Co-Attention and Co-Excitation | NeurIPS 2019 | PASCAL VOC & MS COCO | [PDF](https://proceedings.neurips.cc/paper/2019/file/92af93f73faf3cefc129b6bc55a748a9-Paper.pdf) | [CODE](https://github.com/timy90022/One-Shot-Object-Detection) |

### 2018

| Title | Venue | Dataset | PDF | CODE |

| :-----|:-----:|:---:|:---:|:----:|

| Few-example object detection with model communication | TPAMI 2018 | PASCAL VOC & MS COCO & ILSVRC | [PDF](https://arxiv.org/pdf/1706.08249.pdf) | - |

| LSTD: A Low-Shot Transfer Detector for Object Detection | AAAI 2018 | PASCAL VOC & MS COCO & ImageNet2015 | [PDF](https://ojs.aaai.org/index.php/AAAI/article/view/11716/11575) | - |

##  Datasets

Most few-shot object detection papers usually follow the experimental setup in 《[Meta R-CNN : Towards General Solver for Instance-level Low-shot Learning](https://openaccess.thecvf.com/content_ICCV_2019/papers/Yan_Meta_R-CNN_Towards_General_Solver_for_Instance-Level_Low-Shot_Learning_ICCV_2019_paper.pdf)》 and 《[Few-shot Object Detection via Feature Reweighting](https://openaccess.thecvf.com/content_ICCV_2019/papers/Kang_Few-Shot_Object_Detection_via_Feature_Reweighting_ICCV_2019_paper.pdf)》 and conduct experiments on PASCAL VOC and MS COCO datasets.

### PASCAL VOC

For Pascal VOC, the model is trained on the trainval sets of VOC [2007](https://link.springer.com/article/10.1007/s11263-014-0733-5) and [2012](https://link.springer.com/article/10.1007/s11263-009-0275-4), and tested on VOC 2007 test set. The dataset is partitioned into three base/novel splits, where 5 categories are selected as novel classes and others are base classes. The novel classes in each split are as follows:

| Split | Novel Class |

| :-----:|:-----------:|

| 1 | bird, bus, cow, mbike, sofa |

| 2 | aero, bottle, cow, horse, sofa |

| 3 | boat, cat, mbike, sheep, sofa |

### MS COCO

[MS COCO](https://link.springer.com/chapter/10.1007/978-3-319-10602-1_48) with 80 object categories including the 20 categories in PASCAL VOC. The 20 classes included in PASCAL VOC are set as novel classes, then the rest 60 classes in COCO are as base classes. The union of 80k train images and a 35k subset of validation images (trainval35k) are used for training, and the evaluation is based on the remaining 5k val images (minival).

##  Acknowledgements

Thanks to [Yongqiang Mao](https://wingkeungm.github.io/) for the ideas and templates.