Methods › Computer Vision › Region Proposal › Selective Search
Selective Search
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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
- Add all bounding boxes corresponding to segmented parts to the list of regional proposals
- Group adjacent segments based on similarity
- Go to step 1
At 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.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Near matches the lookup lists, each a different name: SEArch; SEARCH-R; K-Search; W-SEARCH; MR-Search; SEARCH-P1; Search-o1; Search-E1.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 23 · with a code link: 12 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (2 of 23 tagged: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 23 of 23, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
A Realistic Protocol for Evaluation of Weakly Supervised Object Localization 15 Apr 2024 · 1 repository · arXiv:2404.10034
-
Self-Improving Safety Performance of Reinforcement Learning Based Driving with Black-Box Verification Algorithms 29 Oct 2022 · 2 repositories · arXiv:2210.16575
-
Super-Resolution Based Patch-Free 3D Image Segmentation with High-Frequency Guidance 26 Oct 2022 · 1 repository · arXiv:2210.14645
-
MICO: Selective Search with Mutual Information Co-training 9 Sep 2022 · 1 repository · arXiv:2209.04378
-
Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning 9 May 2022 · 0 repositories · arXiv:2205.04042
-
Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning 26 Nov 2021 · 1 repository · arXiv:2111.13651
-
DETReg: Unsupervised Pretraining with Region Priors for Object Detection 8 Jun 2021 · 1 repository · arXiv:2106.04550Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples) · 1 pointer-only (licence)
-
Aligning Pretraining for Detection via Object-Level Contrastive Learning 4 Jun 2021 · 2 repositories · arXiv:2106.02637Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples) · 3 pointer-only (licence)
-
An Ultra Lightweight CNN for Low Resource Circuit Component Recognition 1 Oct 2020 · 0 repositories · arXiv:2010.00505
-
Learning Objectness from Sonar Images for Class-Independent Object Detection 1 Jul 2019 · 0 repositories · arXiv:1907.00734
-
You Reap What You Sow: Using Videos to Generate High Precision Object Proposals for Weakly-Supervised Object Detection 1 Jun 2019 · 0 repositories
-
RRPN: Radar Region Proposal Network for Object Detection in Autonomous Vehicles 1 May 2019 · 1 repository · arXiv:1905.00526
-
Automatic Handgun Detection in X-ray Images using Bag of Words Model with Selective Search 4 Mar 2019 · 0 repositories · arXiv:1903.01322
-
Semantic Hierarchical Priors for Intrinsic Image Decomposition 11 Feb 2019 · 0 repositories · arXiv:1902.03830
-
Learning Position Evaluation Functions Used in Monte Carlo Softmax Search 30 Jan 2019 · 0 repositories · arXiv:1901.10706
-
Deep Multiple Instance Learning for Zero-shot Image Tagging 16 Mar 2018 · 1 repository · arXiv:1803.06051
-
ME R-CNN: Multi-Expert R-CNN for Object Detection 4 Apr 2017 · 0 repositories · arXiv:1704.01069
-
Deep Learning the Indus Script 2 Feb 2017 · 1 repository · arXiv:1702.00523
-
A MultiPath Network for Object Detection 7 Apr 2016 · 1 repository · arXiv:1604.02135
-
Diversity in Object Proposals 14 Mar 2016 · 0 repositories · arXiv:1603.04308
-
Evaluation of Object Detection Proposals Under Condition Variations 10 Dec 2015 · 0 repositories · arXiv:1512.03424
-
Unsupervised Tube Extraction Using Transductive Learning and Dense Trajectories 1 Dec 2015 · 1 repository
-
Boosting Convolutional Features for Robust Object Proposals 21 Mar 2015 · 0 repositories · arXiv:1503.06350
Tasks archive 2025-07-28
20 shown of 48 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections