{"url":"/task/object-detection-1","name":"object-detection","slug":"object-detection-1","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":10514,"papers_with_code":4285,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":9,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/ip102","name":"IP102","full_name":"","num_papers_in_archive":22},{"url":"/dataset/rf100","name":"RF100","full_name":"Roboflow 100","num_papers_in_archive":5},{"url":"/dataset/diamos-plant","name":"DiaMOS Plant","full_name":"A Dataset for Diagnosis and Monitoring Plant Disease","num_papers_in_archive":4},{"url":"/dataset/br35h-brain-tumor-detection-2020","name":"Br35H :: Brain Tumor Detection 2020","full_name":"Br35H :: Brain Tumor Detection 2020","num_papers_in_archive":3},{"url":"/dataset/aodraw","name":"AODRaw","full_name":"Adverse condition Object Detection with RAW images","num_papers_in_archive":1},{"url":"/dataset/gensc-6g","name":"GenSC-6G","full_name":"","num_papers_in_archive":1},{"url":"/dataset/m5-malaria-dataset","name":"M5-Malaria Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/tea-sickness-object-detection","name":"Tea sickness - object detection","full_name":"","num_papers_in_archive":1},{"url":"/dataset/underwater-object-detection-dataset","name":"Underwater Object Detection Dataset","full_name":"","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[],"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":4285,"tagged_in_all":10514,"items":[{"url":"/paper/res2net-a-new-multi-scale-backbone","title":"Res2Net: A New Multi-scale Backbone Architecture","date":"2019-04-02","arxiv_id":"1904.01169","repositories_listed":34,"syntology":{"n":9,"n_ran":3,"n_unverified":6,"n_pointer_only":9}},{"url":"/paper/mobilevit-light-weight-general-purpose-and","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","date":"2021-10-05","arxiv_id":"2110.02178","repositories_listed":31,"syntology":{"n":68,"n_ran":53,"n_unverified":15,"n_pointer_only":18}},{"url":"/paper/mnasnet-platform-aware-neural-architecture","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","date":"2018-07-31","arxiv_id":"1807.11626","repositories_listed":29,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":2}},{"url":"/paper/hardnet-a-low-memory-traffic-network","title":"HarDNet: A Low Memory Traffic Network","date":"2019-09-03","arxiv_id":"1909.00948","repositories_listed":24,"syntology":null},{"url":"/paper/group-normalization","title":"Group Normalization","date":"2018-03-22","arxiv_id":"1803.08494","repositories_listed":22,"syntology":{"n":15,"n_ran":5,"n_unverified":10,"n_pointer_only":4}},{"url":"/paper/visual-attention-network","title":"Visual Attention Network","date":"2022-02-20","arxiv_id":"2202.09741","repositories_listed":21,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/distance-iou-loss-faster-and-better-learning","title":"Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression","date":"2019-11-19","arxiv_id":"1911.08287","repositories_listed":20,"syntology":{"n":25,"n_ran":4,"n_unverified":21,"n_pointer_only":6}},{"url":"/paper/centernet-object-detection-with-keypoint","title":"CenterNet: Keypoint Triplets for Object Detection","date":"2019-04-17","arxiv_id":"1904.08189","repositories_listed":20,"syntology":{"n":11,"n_ran":2,"n_unverified":9,"n_pointer_only":2}},{"url":"/paper/randaugment-practical-data-augmentation-with","title":"RandAugment: Practical automated data augmentation with a reduced search space","date":"2019-09-30","arxiv_id":"1909.13719","repositories_listed":19,"syntology":{"n":65,"n_ran":58,"n_unverified":7,"n_pointer_only":17}},{"url":"/paper/solov2-dynamic-faster-and-stronger","title":"SOLOv2: Dynamic and Fast Instance Segmentation","date":"2020-03-23","arxiv_id":"2003.10152","repositories_listed":18,"syntology":{"n":38,"n_ran":15,"n_unverified":23,"n_pointer_only":24}},{"url":"/paper/pointpillars-fast-encoders-for-object","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","date":"2018-12-14","arxiv_id":"1812.05784","repositories_listed":18,"syntology":{"n":15,"n_ran":2,"n_unverified":13,"n_pointer_only":1}},{"url":"/paper/random-erasing-data-augmentation","title":"Random Erasing Data Augmentation","date":"2017-08-16","arxiv_id":"1708.04896","repositories_listed":18,"syntology":null},{"url":"/paper/semantic-image-segmentation-with-deep","title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","date":"2014-12-22","arxiv_id":"1412.7062","repositories_listed":18,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/how-to-train-your-vit-data-augmentation-and","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","date":"2021-06-18","arxiv_id":"2106.10270","repositories_listed":16,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/filter-response-normalization-layer","title":"Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks","date":"2019-11-21","arxiv_id":"1911.09737","repositories_listed":16,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/nuscenes-a-multimodal-dataset-for-autonomous","title":"nuScenes: A multimodal dataset for autonomous driving","date":"2019-03-26","arxiv_id":"1903.11027","repositories_listed":16,"syntology":{"n":17,"n_ran":1,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/single-shot-refinement-neural-network-for","title":"Single-Shot Refinement Neural Network for Object Detection","date":"2017-11-18","arxiv_id":"1711.06897","repositories_listed":16,"syntology":null},{"url":"/paper/vision-mamba-efficient-visual-representation","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","date":"2024-01-17","arxiv_id":"2401.09417","repositories_listed":15,"syntology":{"n":13,"n_ran":2,"n_unverified":11,"n_pointer_only":1}},{"url":"/paper/maxvit-multi-axis-vision-transformer","title":"MaxViT: Multi-Axis Vision Transformer","date":"2022-04-04","arxiv_id":"2204.01697","repositories_listed":15,"syntology":{"n":53,"n_ran":33,"n_unverified":20,"n_pointer_only":9}},{"url":"/paper/unsupervised-feature-learning-via-non","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","date":"2018-05-05","arxiv_id":"1805.01978","repositories_listed":15,"syntology":{"n":23,"n_ran":19,"n_unverified":4,"n_pointer_only":16}},{"url":"/paper/rtmdet-an-empirical-study-of-designing-real","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","date":"2022-12-14","arxiv_id":"2212.07784","repositories_listed":14,"syntology":{"n":20,"n_ran":3,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/strongsort-make-deepsort-great-again","title":"StrongSORT: Make DeepSORT Great Again","date":"2022-02-28","arxiv_id":"2202.13514","repositories_listed":14,"syntology":{"n":20,"n_ran":3,"n_unverified":17,"n_pointer_only":2}},{"url":"/paper/190409925","title":"Attention Augmented Convolutional Networks","date":"2019-04-22","arxiv_id":"1904.09925","repositories_listed":14,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/speedaccuracy-trade-offs-for-modern","title":"Speed/accuracy trade-offs for modern convolutional object detectors","date":"2016-11-30","arxiv_id":"1611.10012","repositories_listed":14,"syntology":null},{"url":"/paper/imagenet-large-scale-visual-recognition","title":"ImageNet Large Scale Visual Recognition Challenge","date":"2014-09-01","arxiv_id":"1409.0575","repositories_listed":14,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/spatial-pyramid-pooling-in-deep-convolutional","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","date":"2014-06-18","arxiv_id":"1406.4729","repositories_listed":14,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/bottleneck-transformers-for-visual","title":"Bottleneck Transformers for Visual Recognition","date":"2021-01-27","arxiv_id":"2101.11605","repositories_listed":13,"syntology":{"n":49,"n_ran":26,"n_unverified":23,"n_pointer_only":8}},{"url":"/paper/center-based-3d-object-detection-and-tracking","title":"Center-based 3D Object Detection and Tracking","date":"2020-06-19","arxiv_id":"2006.11275","repositories_listed":13,"syntology":{"n":22,"n_ran":7,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/spinenet-learning-scale-permuted-backbone-for","title":"SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization","date":"2019-12-10","arxiv_id":"1912.05027","repositories_listed":13,"syntology":null},{"url":"/paper/bridging-the-gap-between-anchor-based-and","title":"Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection","date":"2019-12-05","arxiv_id":"1912.02424","repositories_listed":13,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}],"syntology_records":25,"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"}}