{"url":"/task/small-object-detection","name":"Small Object Detection","slug":"small-object-detection","description_markdown":"**Small Object Detection** is a computer vision task that involves detecting and localizing small objects in images or videos. This task is challenging due to the small size and low resolution of the objects, as well as other factors such as occlusion, background clutter, and variations in lighting conditions.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Feature-Fused SSD](https://arxiv.org/pdf/1709.05054v3.pdf) )</span>","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":152,"papers_with_code":60,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":13,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/small-object-detection-on-sod4sb-private-test","slug":"small-object-detection-on-sod4sb-private-test","dataset":"SOD4SB Private Test","dataset_url":"/dataset/sod4sb","rows_in_archive":5,"metrics":["AP50"],"first_row_in_archive_order":{"model":"Weighted Box Fusion (WBF)","paper_title":"Ensemble Fusion for Small Object Detection","paper_url":"/paper/ensemble-fusion-for-small-object-detection","paper_date":"2023-08-22","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/small-object-detection-on-sod4sb-public-test-1","slug":"small-object-detection-on-sod4sb-public-test-1","dataset":"SOD4SB Public Test","dataset_url":"/dataset/sod4sb","rows_in_archive":5,"metrics":["AP50"],"first_row_in_archive_order":{"model":"Weighted Box Fusion (WBF)","paper_title":"Ensemble Fusion for Small Object Detection","paper_url":"/paper/ensemble-fusion-for-small-object-detection","paper_date":"2023-08-22","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/small-object-detection-on-bee4exp-honeybee","slug":"small-object-detection-on-bee4exp-honeybee","dataset":"Bee4Exp Honeybee Detection","dataset_url":"/dataset/bee4exp-honeybee-detection","rows_in_archive":1,"metrics":["Average F1"],"first_row_in_archive_order":{"model":"BeeDetector","paper_title":"A Method for Detection of Small Moving Objects in UAV Videos","paper_url":"/paper/a-method-for-detection-of-small-moving","paper_date":"2021-02-11","arxiv_id":null,"code_links":[{"title":"vladan-stojnic/Detection-of-Small-Flying-Objects-in-UAV-Videos","url":"https://github.com/vladan-stojnic/Detection-of-Small-Flying-Objects-in-UAV-Videos"}],"syntology":null}},{"leaderboard":"/sota/small-object-detection-on-soda-d","slug":"small-object-detection-on-soda-d","dataset":"SODA-D","dataset_url":"/dataset/soda-d","rows_in_archive":1,"metrics":["mAP@0.5:0.95"],"first_row_in_archive_order":{"model":"CFINet","paper_title":"Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning","paper_url":"/paper/small-object-detection-via-coarse-to-fine","paper_date":"2023-08-18","arxiv_id":"2308.09534","code_links":[{"title":"shaunyuan22/cfinet","url":"https://github.com/shaunyuan22/cfinet"}],"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/dota","name":"DOTA","full_name":"Dataset for Object deTection in Aerial Images","num_papers_in_archive":293},{"url":"/dataset/isaid","name":"iSAID","full_name":"","num_papers_in_archive":81},{"url":"/dataset/soda-a","name":"SODA-A","full_name":"","num_papers_in_archive":7},{"url":"/dataset/rf100","name":"RF100","full_name":"Roboflow 100","num_papers_in_archive":5},{"url":"/dataset/soda-d","name":"SODA-D","full_name":"","num_papers_in_archive":5},{"url":"/dataset/sod4sb","name":"SOD4SB","full_name":"Small Object Detection for Spotting Birds","num_papers_in_archive":4},{"url":"/dataset/aircraft-context-dataset","name":"Aircraft Context Dataset","full_name":"","num_papers_in_archive":3},{"url":"/dataset/evd4uav","name":"EVD4UAV","full_name":"","num_papers_in_archive":2},{"url":"/dataset/apron-dataset","name":"Apron Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/bee4exp-honeybee-detection","name":"Bee4Exp Honeybee Detection","full_name":"Bee4Exp Honeybee Detection","num_papers_in_archive":1},{"url":"/dataset/blood-cell-detection-dataset","name":"Blood Cell Detection Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/sfchd","name":"SFCHD","full_name":"","num_papers_in_archive":1},{"url":"/dataset/usc-grad-stddb","name":"USC-GRAD-STDdb","full_name":"Small Target Detection database","num_papers_in_archive":1}],"subtasks":[{"url":"/task/rice-grain-disease-detection","name":"Rice Grain Disease 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":60,"tagged_in_all":152,"items":[{"url":"/paper/an-energy-and-gpu-computation-efficient","title":"An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection","date":"2019-04-22","arxiv_id":"1904.09730","repositories_listed":12,"syntology":null},{"url":"/paper/slicing-aided-hyper-inference-and-fine-tuning","title":"Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection","date":"2022-02-14","arxiv_id":"2202.06934","repositories_listed":6,"syntology":{"n":19,"n_ran":1,"n_unverified":18,"n_pointer_only":0}},{"url":"/paper/augmentation-for-small-object-detection","title":"Augmentation for small object detection","date":"2019-02-19","arxiv_id":"1902.07296","repositories_listed":5,"syntology":null},{"url":"/paper/small-object-detection-in-remote-sensing","title":"Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network","date":"2020-03-20","arxiv_id":"2003.09085","repositories_listed":4,"syntology":null},{"url":"/paper/small-object-detection-via-pixel-level","title":"Small Object Detection via Pixel Level Balancing With Applications to Blood Cell Detection","date":"2022-06-17","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/a-normalized-gaussian-wasserstein-distance","title":"A Normalized Gaussian Wasserstein Distance for Tiny Object Detection","date":"2021-10-26","arxiv_id":"2110.13389","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/local-contrast-and-global-contextual","title":"Local Contrast and Global Contextual Information Make Infrared Small Object Salient Again","date":"2023-01-28","arxiv_id":"2301.12093","repositories_listed":2,"syntology":null},{"url":"/paper/voxel-mae-masked-autoencoders-for-pre","title":"Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders","date":"2022-06-20","arxiv_id":"2206.09900","repositories_listed":2,"syntology":{"n":9,"n_ran":1,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/yolo-z-improving-small-object-detection-in","title":"YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles","date":"2021-12-22","arxiv_id":"2112.11798","repositories_listed":2,"syntology":null},{"url":"/paper/rethinking-rotated-object-detection-with","title":"Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss","date":"2021-01-28","arxiv_id":"2101.11952","repositories_listed":2,"syntology":null},{"url":"/paper/real-time-gun-detection-in-cctv-an-open","title":"Real-time gun detection in CCTV: An open problem","date":"2020-12-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/vme-a-satellite-imagery-dataset-and-benchmark","title":"VME: A Satellite Imagery Dataset and Benchmark for Detecting Vehicles in the Middle East and Beyond","date":"2025-05-28","arxiv_id":"2505.22353","repositories_listed":1,"syntology":null},{"url":"/paper/self-prompting-analogical-reasoning-for-uav","title":"self-prompting analogical reasoning for uav object detection","date":"2025-04-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/remdet-rethinking-efficient-model-design-for","title":"RemDet: Rethinking Efficient Model Design for UAV Object Detection","date":"2024-12-13","arxiv_id":"2412.10040","repositories_listed":1,"syntology":null},{"url":"/paper/pansr-an-object-centric-mask-transformer-for","title":"PanSR: An Object-Centric Mask Transformer for Panoptic Segmentation","date":"2024-12-13","arxiv_id":"2412.10589","repositories_listed":1,"syntology":null},{"url":"/paper/local-global-attention-an-adaptive-mechanism","title":"Local-Global Attention: An Adaptive Mechanism for Multi-Scale Feature Integration","date":"2024-11-14","arxiv_id":"2411.09604","repositories_listed":1,"syntology":null},{"url":"/paper/pk-yolo-pretrained-knowledge-guided-yolo-for","title":"PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplanar MRI Slices","date":"2024-10-29","arxiv_id":"2410.21822","repositories_listed":1,"syntology":{"n":34,"n_ran":13,"n_unverified":21,"n_pointer_only":34}},{"url":"/paper/unleashing-the-power-of-generic-segmentation","title":"Unleashing the Power of Generic Segmentation Models: A Simple Baseline for Infrared Small Target Detection","date":"2024-09-07","arxiv_id":"2409.04714","repositories_listed":1,"syntology":null},{"url":"/paper/a-lightweight-insulator-defect-detection","title":"A Lightweight Insulator Defect Detection Model Based on Drone Images","date":"2024-08-26","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/idd-yolov5-a-lightweight-insulator-defect","title":"IDD-YOLOv5: A Lightweight Insulator Defect Real-time Detection Algorithm","date":"2024-08-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/sod-yolov8-enhancing-yolov8-for-small-object","title":"SOD-YOLOv8 -- Enhancing YOLOv8 for Small Object Detection in Traffic Scenes","date":"2024-08-08","arxiv_id":"2408.04786","repositories_listed":1,"syntology":null},{"url":"/paper/cross-layer-feature-pyramid-transformer-for","title":"Cross-Layer Feature Pyramid Transformer for Small Object Detection in Aerial Images","date":"2024-07-29","arxiv_id":"2407.19696","repositories_listed":1,"syntology":null},{"url":"/paper/esod-efficient-small-object-detection-on-high","title":"ESOD: Efficient Small Object Detection on High-Resolution Images","date":"2024-07-23","arxiv_id":"2407.16424","repositories_listed":1,"syntology":null},{"url":"/paper/visible-thermal-tiny-object-detection-a","title":"Visible-Thermal Tiny Object Detection: A Benchmark Dataset and Baselines","date":"2024-06-20","arxiv_id":"2406.14482","repositories_listed":1,"syntology":null},{"url":"/paper/sense-less-generate-more-pre-training-lidar","title":"Sense Less, Generate More: Pre-training LiDAR Perception with Masked Autoencoders for Ultra-Efficient 3D Sensing","date":"2024-06-12","arxiv_id":"2406.07833","repositories_listed":1,"syntology":null},{"url":"/paper/mwirstd-a-mwir-small-target-detection-dataset","title":"MWIRSTD: A MWIR Small Target Detection Dataset","date":"2024-06-12","arxiv_id":"2406.08063","repositories_listed":1,"syntology":null},{"url":"/paper/select-mosaic-data-augmentation-method-for","title":"Select-Mosaic: Data Augmentation Method for Dense Small Object Scenes","date":"2024-06-08","arxiv_id":"2406.05412","repositories_listed":1,"syntology":null},{"url":"/paper/constellation-dataset-benchmarking-high","title":"Constellation Dataset: Benchmarking High-Altitude Object Detection for an Urban Intersection","date":"2024-04-25","arxiv_id":"2404.16944","repositories_listed":1,"syntology":null},{"url":"/paper/fool-addressing-the-downlink-bottleneck-in","title":"FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression","date":"2024-03-25","arxiv_id":"2403.16677","repositories_listed":1,"syntology":null},{"url":"/paper/hcf-net-hierarchical-context-fusion-network","title":"HCF-Net: Hierarchical Context Fusion Network for Infrared Small Object Detection","date":"2024-03-16","arxiv_id":"2403.10778","repositories_listed":1,"syntology":null}],"syntology_records":4,"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"}}