AI Paper Atlas

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

Weakly Supervised Semantic Segmentation with Boundary Exploration

Liyi Chen, Weiwei Wu, Chenchen Fu, Xiao Han, Yuntao Zhang

ECCV 2020 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 194 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 exploration (BENet-constrained propagation) (ablation)attention-pooling CAM · PASCAL VOC 2012 train (pseudo labels)mIoU: 50.4% to 66.4%Improved
add attention-pooling CAM instead of GAP CAM (ablation)CAM · PASCAL VOC 2012 train (pseudo labels)mIoU: 49.6% to 50.4%Improved
add attention pooling on top of boundary exploration (ablation)CAM + boundary exploration · PASCAL VOC 2012 train (pseudo labels)mIoU: 65.7 -> 66.4Improved
add dCRF post-processing of pseudo labels (ablation)BES · PASCAL VOC 2012 train (pseudo labels)mIoU: 66.4% to 67.2%Improved
vary theta_diff and theta_scale in boundary label synthesis (ablation)BES · PASCAL VOC 2012 train (pseudo labels)mIoU: 65.0 to 66.4 across gridNo clear effect
increase attention intensity k beyond a small value (ablation)attention-pooling CAM · PASCAL VOC 2012 train (pseudo labels)mIoUHurt
small attention intensity k versus GAP-based CAM (ablation)attention-pooling CAM · PASCAL VOC 2012 train (pseudo labels)mIoUImproved
use BES labels to train DeepLab-ASPP instead of IRNet labelsDeepLab-ASPP · PASCAL VOC 2012 valmIoU: 63.5 -> 65.7Improved

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