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.
Papers archive 2025-07-28
23 shown of 23, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
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 ran 4 of 7 samples · 3 unverified
-
Aligning Pretraining for Detection via Object-Level Contrastive Learning 4 Jun 2021 · 2 repositories · arXiv:2106.02637Syntology ran 4 of 6 samples · 2 unverified · 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