AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Exploit Visual Dependency Relations for Semantic Segmentation

Mingyuan Liu, Dan Schonfeld, Wei Tang

CVPR 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Visual relationship and scene graph detection · 26 citations (OpenAlex)

Check 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 intra-class, inter-class, and global dependency reasoning (ablation)ResNet-50 segmentation network · Cityscapes validationmIoU%: 71.38 -> 76.32Improved
Add intra-class dependency reasoning (ablation)ResNet-50 segmentation network · Cityscapes validationmIoU%: 71.38 -> 73.54Improved
Add inter-class dependency reasoning (ablation)ResNet-50 segmentation network · Cityscapes validationmIoU%: 71.38 -> 72.55Improved
Add global dependency reasoning (ablation)ResNet-50 segmentation network · Cityscapes validationmIoU%: 71.38 -> 74.92Improved
Add intermediate segmentation loss Lseg (ablation)DependencyNet · Cityscapes validationmIoU%: 76.32 -> 77.66Improved
Use group weighted convolutions instead of conventional convolutions for inter-class reasoning (ablation)DependencyNet · Cityscapes validationmIoU%: 76.14 -> 77.66Improved
Use Gconn rather than Gedge as the dependency graph (ablation)DependencyNet inter-class reasoning · Cityscapes validationmIoU%: 77.41 -> 77.66Improved
Use supervised category-specific representations rather than Class Center Mapping (ablation)DependencyNet · Cityscapes validationmIoU%: 74.61 -> 77.66Improved
Add dependency reasoningResNet-101 · BDD100K validationmIoU%: 62.3 -> 63.9Improved
Add dependency reasoningResNet-101 · Cityscapes validationmIoU%: 76.44 -> 79.15Improved
Add multi-scale inference (ablation)DependencyNet with ResNet-101 · Cityscapes validationmIoU%: 79.15 -> 80.48Improved
Add ASPP alongside DependencyNet and multi-scale inference (ablation)DependencyNet with ResNet-101 · Cityscapes validationmIoU%: 80.48 -> 82.01Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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