AI Paper Atlas

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

FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence

Seungryong Kim, Dongbo Min, Bumsub Ham, Sangryul Jeon, Stephen Lin, Kwanghoon Sohn

CVPR 2017 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 134 citations (OpenAlex)

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
Replace VGG descriptors with FCSSVGG-Net descriptor with fixed SIFT Flow optimization · Taniai averagematching accuracy: 0.535 -> 0.660Improved
Use Proposal Flow optimization instead of SIFT FlowFCSS · Proposal Flow benchmark, α=0.1PCK: 0.532 -> 0.584Improved
Use Proposal Flow optimization instead of SIFT FlowFCSS · PASCAL-VOC part, PCK α=0.1PCK: 0.47 -> 0.46No clear effect
Use learned sampling patterns rather than random sampling patterns (ablation)VGG with single-scale CSS · Taniai averagematching accuracy: 0.551 -> 0.573Improved
Add learned single-scale CSS (ablation)VGG-Net descriptor · Taniai averagematching accuracy: 0.535 -> 0.573Improved
Add multi-scale CSS instead of single-scale CSS (ablation)VGG-Net descriptor · Taniai averagematching accuracy: 0.573 -> 0.610Improved
Add multi-scale CSS instead of single-scale CSS (ablation)VGG-Net descriptor · Proposal Flow benchmark, α=0.1PCK: 0.422 -> 0.514Improved

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