{"url":"/method/selective-search","slug":"selective-search","name":"Selective Search","full_name":"Selective Search","full_name_withheld":false,"description_markdown":"**Selective Search** is a region proposal algorithm for object detection tasks. It starts by over-segmenting the image based on intensity of the pixels using a graph-based segmentation method by Felzenszwalb and Huttenlocher. Selective Search then takes these oversegments as initial input and performs the following steps\r\n\r\n1. Add all bounding boxes corresponding to segmented parts to the list of regional proposals\r\n2. Group adjacent segments based on similarity\r\n3. Go to step 1\r\n\r\nAt each iteration, larger segments are formed and added to the list of region proposals. Hence we create region proposals from smaller segments to larger segments in a bottom-up approach. This is what we mean by computing “hierarchical” segmentations using Felzenszwalb and Huttenlocher’s oversegments.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":null,"title":null,"url_on_a_paper_host":false},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Region Proposal","url":"/methods/category/region-proposal","pwc_aliases":[]}],"n_papers_tagged":23,"archive_num_papers":23,"papers_newest_first":[{"paper":"/paper/realistic-model-selection-for-weakly","title":"A Realistic Protocol for Evaluation of Weakly Supervised Object Localization","date":"2024-04-15","arxiv_id":"2404.10034","n_code_links":1,"syntology":null},{"paper":"/paper/self-improving-safety-performance-of","title":"Self-Improving Safety Performance of Reinforcement Learning Based Driving with Black-Box Verification Algorithms","date":"2022-10-29","arxiv_id":"2210.16575","n_code_links":2,"syntology":null},{"paper":"/paper/super-resolution-based-patch-free-3d-medical","title":"Super-Resolution Based Patch-Free 3D Image Segmentation with High-Frequency Guidance","date":"2022-10-26","arxiv_id":"2210.14645","n_code_links":1,"syntology":null},{"paper":"/paper/mico-selective-search-with-mutual-information","title":"MICO: Selective Search with Mutual Information Co-training","date":"2022-09-09","arxiv_id":"2209.04378","n_code_links":1,"syntology":null},{"paper":null,"title":"Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning","date":"2022-05-09","arxiv_id":"2205.04042","n_code_links":0,"syntology":null},{"paper":"/paper/contrastive-object-level-pre-training-with","title":"Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning","date":"2021-11-26","arxiv_id":"2111.13651","n_code_links":1,"syntology":null},{"paper":"/paper/detreg-unsupervised-pretraining-with-region","title":"DETReg: Unsupervised Pretraining with Region Priors for Object Detection","date":"2021-06-08","arxiv_id":"2106.04550","n_code_links":1,"syntology":{"ran":4,"of":7,"unverified":3,"pointer_only":0}},{"paper":"/paper/aligning-pretraining-for-detection-via-object","title":"Aligning Pretraining for Detection via Object-Level Contrastive Learning","date":"2021-06-04","arxiv_id":"2106.02637","n_code_links":2,"syntology":{"ran":4,"of":6,"unverified":2,"pointer_only":3}},{"paper":null,"title":"An Ultra Lightweight CNN for Low Resource Circuit Component Recognition","date":"2020-10-01","arxiv_id":"2010.00505","n_code_links":0,"syntology":null},{"paper":null,"title":"Learning Objectness from Sonar Images for Class-Independent Object Detection","date":"2019-07-01","arxiv_id":"1907.00734","n_code_links":0,"syntology":null},{"paper":"/paper/you-reap-what-you-sow-using-videos-to","title":"You Reap What You Sow: Using Videos to Generate High Precision Object Proposals for Weakly-Supervised Object Detection","date":"2019-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/rrpn-radar-region-proposal-network-for-object","title":"RRPN: Radar Region Proposal Network for Object Detection in Autonomous Vehicles","date":"2019-05-01","arxiv_id":"1905.00526","n_code_links":1,"syntology":null},{"paper":null,"title":"Automatic Handgun Detection in X-ray Images using Bag of Words Model with Selective Search","date":"2019-03-04","arxiv_id":"1903.01322","n_code_links":0,"syntology":null},{"paper":null,"title":"Semantic Hierarchical Priors for Intrinsic Image Decomposition","date":"2019-02-11","arxiv_id":"1902.03830","n_code_links":0,"syntology":null},{"paper":null,"title":"Learning Position Evaluation Functions Used in Monte Carlo Softmax Search","date":"2019-01-30","arxiv_id":"1901.10706","n_code_links":0,"syntology":null},{"paper":"/paper/deep-multiple-instance-learning-for-zero-shot","title":"Deep Multiple Instance Learning for Zero-shot Image Tagging","date":"2018-03-16","arxiv_id":"1803.06051","n_code_links":1,"syntology":null},{"paper":null,"title":"ME R-CNN: Multi-Expert R-CNN for Object Detection","date":"2017-04-04","arxiv_id":"1704.01069","n_code_links":0,"syntology":null},{"paper":"/paper/deep-learning-the-indus-script","title":"Deep Learning the Indus Script","date":"2017-02-02","arxiv_id":"1702.00523","n_code_links":1,"syntology":null},{"paper":"/paper/a-multipath-network-for-object-detection","title":"A MultiPath Network for Object Detection","date":"2016-04-07","arxiv_id":"1604.02135","n_code_links":1,"syntology":null},{"paper":null,"title":"Diversity in Object Proposals","date":"2016-03-14","arxiv_id":"1603.04308","n_code_links":0,"syntology":null},{"paper":null,"title":"Evaluation of Object Detection Proposals Under Condition Variations","date":"2015-12-10","arxiv_id":"1512.03424","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-tube-extraction-using","title":"Unsupervised Tube Extraction Using Transductive Learning and Dense Trajectories","date":"2015-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Boosting Convolutional Features for Robust Object Proposals","date":"2015-03-21","arxiv_id":"1503.06350","n_code_links":0,"syntology":null}],"papers_shown":23,"tasks":[{"task":"/task/object","name":"Object","papers":11},{"task":"/task/object-detection","name":"Object Detection","papers":11},{"task":"/task/object-detection-1","name":"object-detection","papers":11},{"task":"/task/region-proposal","name":"Region Proposal","papers":4},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":2},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":2},{"task":"/task/diversity","name":"Diversity","papers":2},{"task":"/task/few-shot-object-detection","name":"Few-Shot Object Detection","papers":2},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":2},{"task":"/task/object-localization","name":"Object Localization","papers":2},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":2},{"task":"/task/autonomous-vehicles","name":"Autonomous Vehicles","papers":1},{"task":"/task/computed-tomography-ct","name":"Computed Tomography (CT)","papers":1},{"task":"/task/deep-learning","name":"Deep Learning","papers":1},{"task":"/task/few-shot-learning","name":"Few-Shot Learning","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/classification","name":"General Classification","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":1}],"tasks_shown":20,"n_tasks":48,"usage_by_year":[{"year":"2015","papers":3},{"year":"2016","papers":2},{"year":"2017","papers":2},{"year":"2018","papers":1},{"year":"2019","papers":6},{"year":"2020","papers":1},{"year":"2021","papers":3},{"year":"2022","papers":4},{"year":"2024","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/selective-search"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}