AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Competing for Pixels: A Self-Play Algorithm for Weakly-Supervised Semantic Segmentation

Shaheer Ullah Saeed, Shiqi Huang, João Ramalhinho, Iani J. M. B. Gayo, Nina Montaña-Brown, Ester Bonmati, Stephen P. Pereira, Brian Ritchie Davidson, Dean C. Barratt, Matthew J. Clarkson, Yipeng Hu

TPAMI 2024 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add self-play opponent agent instead of fixed 0.8 threshold (ablation)RLSP · VOC valmIoU: 70.3 -> 78.9Improved
add repetition and iteration shaping rewards (ablation)RLSP · VOC valmIoU: 75.7 -> 78.9Improved
add iteration-bounding reward on top of repetition reward (ablation)RLSP · VOC valmIoU: 76.4 -> 78.9Improved
add repetition reward on top of iteration reward (ablation)RLSP · VOC valmIoU: 77.7 -> 78.9Improved
add shaping rewards without self-play (ablation)non-self-play variant · VOC valmIoU: 68.8 -> 70.3Improved
increase patch size from 2x2 to 6x6 (ablation)RLSP · VOC valmIoU: 76.4 -> 78.9Improved
increase patch size beyond 6x6 to 8x8 (ablation)RLSP · VOC valmIoU: 78.9 -> 78.3No clear effect
use self-play RL instead of sliding-window with 0.5 thresholdobject presence detector · VOC valmIoU: 64.9 -> 78.9Improved
lower non-self-play selection threshold from 0.8 to 0.2non-SP · VOC valmIoU: 70.3 -> 68.5Hurt
switch backbone from ResNet38 to ResNet101 or VGG16 (ablation)RLSP · VOC valmIoU: reduced performance by 0.5 or 1.2 mIoU pointsNo clear effect
RLSP versus best prior MARSRLSP · CMPS (RE)mDSC: 54.2 -> 58.8Improved
RLSP versus best prior MARSRLSP · VOC testmIoU: 77.2 -> 78.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy