{"url":"/task/few-shot-object-detection","name":"Few-Shot Object Detection","slug":"few-shot-object-detection","description_markdown":"**Few-Shot Object Detection** is a computer vision task that involves detecting objects in images with limited training data. The goal is to train a model on a few examples of each object class and then use the model to detect objects in new images.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":179,"papers_with_code":97,"benchmarks":10,"benchmark_tables_in_archive":10,"benchmark_tables_shown":10,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":8,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/few-shot-object-detection-on-ms-coco-10-shot","slug":"few-shot-object-detection-on-ms-coco-10-shot","dataset":"MS-COCO (10-shot)","dataset_url":"/dataset/coco","rows_in_archive":33,"metrics":["AP"],"first_row_in_archive_order":{"model":"Training-free","paper_title":"No time to train! Training-Free Reference-Based Instance Segmentation","paper_url":"/paper/no-time-to-train-training-free-reference","paper_date":"2025-07-03","arxiv_id":"2507.02798","code_links":[{"title":"miquel-espinosa/no-time-to-train","url":"https://github.com/miquel-espinosa/no-time-to-train"},{"title":"miquel-espinosa/samantics","url":"https://github.com/miquel-espinosa/samantics"}],"syntology":null}},{"leaderboard":"/sota/few-shot-object-detection-on-camo-fs","slug":"few-shot-object-detection-on-camo-fs","dataset":"CAMO-FS","dataset_url":"/dataset/camo-fs","rows_in_archive":26,"metrics":["box AP"],"first_row_in_archive_order":{"model":"FS-CDIS (MTFA+IMS 5-shot)","paper_title":"The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation","paper_url":"/paper/few-shot-camouflaged-animal-detection-and","paper_date":"2023-04-15","arxiv_id":"2304.07444","code_links":[{"title":"danhntd/FS-CDIS","url":"https://github.com/danhntd/FS-CDIS"}],"syntology":null}},{"leaderboard":"/sota/few-shot-object-detection-on-ms-coco-30-shot","slug":"few-shot-object-detection-on-ms-coco-30-shot","dataset":"MS-COCO (30-shot)","dataset_url":null,"rows_in_archive":25,"metrics":["AP"],"first_row_in_archive_order":{"model":"Training-free","paper_title":"No time to train! Training-Free Reference-Based Instance Segmentation","paper_url":"/paper/no-time-to-train-training-free-reference","paper_date":"2025-07-03","arxiv_id":"2507.02798","code_links":[{"title":"miquel-espinosa/no-time-to-train","url":"https://github.com/miquel-espinosa/no-time-to-train"},{"title":"miquel-espinosa/samantics","url":"https://github.com/miquel-espinosa/samantics"}],"syntology":null}},{"leaderboard":"/sota/few-shot-object-detection-on-lvis-v1-0-val","slug":"few-shot-object-detection-on-lvis-v1-0-val","dataset":"LVIS v1.0 val","dataset_url":"/dataset/lvis","rows_in_archive":7,"metrics":["AP","AP50","AP75","APr","APc","APf"],"first_row_in_archive_order":{"model":"best_single_model_val","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/few-shot-object-detection-on-ms-coco-1-shot","slug":"few-shot-object-detection-on-ms-coco-1-shot","dataset":"MS-COCO (1-shot)","dataset_url":null,"rows_in_archive":7,"metrics":["AP"],"first_row_in_archive_order":{"model":"Training-free","paper_title":"No time to train! Training-Free Reference-Based Instance Segmentation","paper_url":"/paper/no-time-to-train-training-free-reference","paper_date":"2025-07-03","arxiv_id":"2507.02798","code_links":[{"title":"miquel-espinosa/no-time-to-train","url":"https://github.com/miquel-espinosa/no-time-to-train"},{"title":"miquel-espinosa/samantics","url":"https://github.com/miquel-espinosa/samantics"}],"syntology":null}},{"leaderboard":"/sota/few-shot-object-detection-on-lvis-v1-0-test","slug":"few-shot-object-detection-on-lvis-v1-0-test","dataset":"LVIS v1.0 test-dev","dataset_url":"/dataset/lvis","rows_in_archive":5,"metrics":["AP","AP50","AP75","APr","APc","APf"],"first_row_in_archive_order":{"model":"TestConsistency","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/few-shot-object-detection-on-odinw-13","slug":"few-shot-object-detection-on-odinw-13","dataset":"ODinW-13","dataset_url":null,"rows_in_archive":3,"metrics":["Average Score"],"first_row_in_archive_order":{"model":"Grounding DINO 1.5 Pro","paper_title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","paper_url":"/paper/grounding-dino-1-5-advance-the-edge-of-open","paper_date":"2024-05-16","arxiv_id":"2405.10300","code_links":[{"title":"mit-han-lab/efficientvit","url":"https://github.com/mit-han-lab/efficientvit"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"idea-research/grounding-dino-1.5-api","url":"https://github.com/idea-research/grounding-dino-1.5-api"}],"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-object-detection-on-odinw-35","slug":"few-shot-object-detection-on-odinw-35","dataset":"ODinW-35","dataset_url":null,"rows_in_archive":3,"metrics":["Average Score"],"first_row_in_archive_order":{"model":"Grounding DINO 1.5 Pro","paper_title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","paper_url":"/paper/grounding-dino-1-5-advance-the-edge-of-open","paper_date":"2024-05-16","arxiv_id":"2405.10300","code_links":[{"title":"mit-han-lab/efficientvit","url":"https://github.com/mit-han-lab/efficientvit"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"idea-research/grounding-dino-1.5-api","url":"https://github.com/idea-research/grounding-dino-1.5-api"}],"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-object-detection-on-coco-2017","slug":"few-shot-object-detection-on-coco-2017","dataset":"COCO 2017","dataset_url":"/dataset/coco","rows_in_archive":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"DETReg (ours)","paper_title":"DETReg: Unsupervised Pretraining with Region Priors for Object Detection","paper_url":"/paper/detreg-unsupervised-pretraining-with-region","paper_date":"2021-06-08","arxiv_id":"2106.04550","code_links":[{"title":"amirbar/detreg","url":"https://github.com/amirbar/detreg"}],"syntology":{"n":7,"n_ran":4,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-object-detection-on-ms-coco-5-shot","slug":"few-shot-object-detection-on-ms-coco-5-shot","dataset":"MS-COCO (5-shot)","dataset_url":null,"rows_in_archive":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"UniFS","paper_title":"UniFS: Universal Few-shot Instance Perception with Point Representations","paper_url":"/paper/unifs-universal-few-shot-instance-perception","paper_date":"2024-04-30","arxiv_id":"2404.19401","code_links":[{"title":"jin-s13/unifs","url":"https://github.com/jin-s13/unifs"}],"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}}}],"datasets":[{"url":"/dataset/coco","name":"COCO (Common Objects in Context)","full_name":"Common Objects in Context","num_papers_in_archive":11922},{"url":"/dataset/lvis","name":"LVIS","full_name":"","num_papers_in_archive":551},{"url":"/dataset/fsod","name":"FSOD","full_name":"Few-Shot Object Detection Dataset","num_papers_in_archive":68},{"url":"/dataset/elevater","name":"ELEVATER","full_name":"Evaluation of Language-augmented Visual Task-level Transfer","num_papers_in_archive":25},{"url":"/dataset/logo-net","name":"LOGO-Net","full_name":"","num_papers_in_archive":3},{"url":"/dataset/banknote-net","name":"BankNote-Net","full_name":"","num_papers_in_archive":1},{"url":"/dataset/camo-fs","name":"CAMO-FS","full_name":"CAMO-FS","num_papers_in_archive":1},{"url":"/dataset/vizwiz-fewshot","name":"VizWiz-FewShot","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/cross-domain-few-shot-object-detection","name":"Cross-Domain Few-Shot Object Detection"}],"parent_tasks":[{"url":"/task/object-detection","name":"Object Detection"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":97,"tagged_in_all":179,"items":[{"url":"/paper/elevater-a-benchmark-and-toolkit-for","title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","date":"2022-04-19","arxiv_id":"2204.08790","repositories_listed":9,"syntology":{"n":20,"n_ran":4,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/frustratingly-simple-few-shot-object","title":"Frustratingly Simple Few-Shot Object Detection","date":"2020-03-16","arxiv_id":"2003.06957","repositories_listed":5,"syntology":{"n":11,"n_ran":3,"n_unverified":8,"n_pointer_only":11}},{"url":"/paper/ntire-2025-challenge-on-cross-domain-few-shot","title":"NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results","date":"2025-04-14","arxiv_id":"2504.10685","repositories_listed":4,"syntology":null},{"url":"/paper/beyond-max-margin-class-margin-equilibrium","title":"Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection","date":"2021-03-08","arxiv_id":"2103.04612","repositories_listed":4,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":6}},{"url":"/paper/multi-scale-positive-sample-refinement-for","title":"Multi-Scale Positive Sample Refinement for Few-Shot Object Detection","date":"2020-07-18","arxiv_id":"2007.09384","repositories_listed":4,"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/few-shot-object-detection-via-feature","title":"Few-shot Object Detection via Feature Reweighting","date":"2018-12-05","arxiv_id":"1812.01866","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/grounding-dino-1-5-advance-the-edge-of-open","title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","date":"2024-05-16","arxiv_id":"2405.10300","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/integral-migrating-pre-trained-transformer","title":"Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection","date":"2022-05-19","arxiv_id":"2205.09613","repositories_listed":3,"syntology":null},{"url":"/paper/grounded-language-image-pre-training","title":"Grounded Language-Image Pre-training","date":"2021-12-07","arxiv_id":"2112.03857","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/few-shot-object-detection-with-attention-rpn","title":"Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector","date":"2019-08-06","arxiv_id":"1908.01998","repositories_listed":3,"syntology":{"n":10,"n_ran":2,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/one-shot-instance-segmentation","title":"One-Shot Instance Segmentation","date":"2018-11-28","arxiv_id":"1811.11507","repositories_listed":3,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/no-time-to-train-training-free-reference","title":"No time to train! Training-Free Reference-Based Instance Segmentation","date":"2025-07-03","arxiv_id":"2507.02798","repositories_listed":2,"syntology":null},{"url":"/paper/cross-domain-few-shot-object-detection-via","title":"Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector","date":"2024-02-05","arxiv_id":"2402.03094","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/task-focused-few-shot-object-detection-for","title":"Mobile Robot Manipulation using Pure Object Detection","date":"2022-01-28","arxiv_id":"2201.12437","repositories_listed":2,"syntology":null},{"url":"/paper/defrcn-decoupled-faster-r-cnn-for-few-shot","title":"DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection","date":"2021-08-20","arxiv_id":"2108.09017","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/meta-faster-r-cnn-towards-accurate-few-shot","title":"Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment","date":"2021-04-15","arxiv_id":"2104.07719","repositories_listed":2,"syntology":null},{"url":"/paper/meta-detr-few-shot-object-detection-via","title":"Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation","date":"2021-03-22","arxiv_id":"2103.11731","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/fsce-few-shot-object-detection-via","title":"FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding","date":"2021-03-10","arxiv_id":"2103.05950","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/few-shot-object-detection-and-viewpoint","title":"Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild","date":"2020-07-23","arxiv_id":"2007.12107","repositories_listed":2,"syntology":{"n":17,"n_ran":1,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/decoupling-classifier-for-boosting-few-shot-1","title":"Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation","date":"2025-05-20","arxiv_id":"2505.14239","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/cdformer-cross-domain-few-shot-object","title":"CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusion","date":"2025-05-02","arxiv_id":"2505.00938","repositories_listed":1,"syntology":null},{"url":"/paper/generalized-semantic-contrastive-learning-via","title":"Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection","date":"2025-04-09","arxiv_id":"2504.07060","repositories_listed":1,"syntology":null},{"url":"/paper/enhance-then-search-an-augmentation-search","title":"Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detection","date":"2025-04-06","arxiv_id":"2504.04517","repositories_listed":1,"syntology":null},{"url":"/paper/visual-rft-visual-reinforcement-fine-tuning","title":"Visual-RFT: Visual Reinforcement Fine-Tuning","date":"2025-03-03","arxiv_id":"2503.01785","repositories_listed":1,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/multi-perspective-data-augmentation-for-few","title":"Multi-Perspective Data Augmentation for Few-shot Object Detection","date":"2025-02-25","arxiv_id":"2502.18195","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/cross-domain-few-shot-object-detection-with","title":"Cross-domain Few-shot Object Detection with Multi-modal Textual Enrichment","date":"2025-02-23","arxiv_id":"2502.16469","repositories_listed":1,"syntology":null},{"url":"/paper/generalization-enhanced-few-shot-object","title":"Generalization-Enhanced Few-Shot Object Detection in Remote Sensing","date":"2025-01-05","arxiv_id":"2501.02474","repositories_listed":1,"syntology":null},{"url":"/paper/simltd-simple-supervised-and-semi-supervised","title":"SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection","date":"2024-12-28","arxiv_id":"2412.20047","repositories_listed":1,"syntology":null},{"url":"/paper/open-vocabulary-vs-closed-set-best-practice","title":"Open-vocabulary vs. Closed-set: Best Practice for Few-shot Object Detection Considering Text Describability","date":"2024-10-20","arxiv_id":"2410.15315","repositories_listed":1,"syntology":null},{"url":"/paper/ps-ttl-prototype-based-soft-labels-and-test","title":"PS-TTL: Prototype-based Soft-labels and Test-Time Learning for Few-shot Object Detection","date":"2024-08-11","arxiv_id":"2408.05674","repositories_listed":1,"syntology":null}],"syntology_records":17,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}