AI Paper Atlas

Research map / Detection and segmentation / CNN features

Multi-Class Part Parsing With Joint Boundary-Semantic Awareness

Yifan Zhao, Jia Li, Yu Zhang, Yonghong Tian

ICCV 2019 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 57 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 boundary-aware spatial selection and semantic channel selection (full BSANet)Deeplabv3 baseline · PASCAL-PartmIoU: 54.03 -> 58.18Improved
add boundary selection alone (ablation)baseline · PASCAL-PartmIoU: 54.03 -> 56.97Improved
add semantic selection alone (ablation)baseline · PASCAL-PartmIoU: 54.03 -> 55.87Improved
add both modules without supervised selection (self-attention) (ablation)baseline · PASCAL-PartmIoU: 54.03 -> 54.59No clear effect
add supervision (boundary and semantic losses) to the selection modules (ablation)BSANet · PASCAL-PartmIoU: 54.59 -> 58.18Improved
add lateral connections between low-level and high-level features (ablation)baseline · Pascal-Person-PartmIoU: 62.83 -> 65.06Improved
replace lateral connections with boundary awareness on all blocks (ablation)lateral-all · Pascal-Person-PartmIoU: 65.06 -> 66.77Improved
add more pyramid blocks to boundary awareness (BA-1 to BA-all) (ablation)BA module · Pascal-Person-PartmIoU: 64.59 -> 66.77Improved
add boundary regularization loss to BA-all (ablation)BA-all · Pascal-Person-PartmIoU: 64.94 -> 66.77Improved
add semantic selection on top of BA-all (ablation)BA-all · Pascal-Person-PartmIoU: 66.77 -> 67.37Improved
add BSANet to ResNet-50 backbone (ablation)Deeplabv3 ResNet-50 · Pascal-Person-PartmIoU: 59.96 -> 62.29Improved
add BSANet to ResNet-101 backbone (ablation)Deeplabv3 ResNet-101 · Pascal-Person-PartmIoU: 62.83 -> 67.37Improved

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