AI Paper Atlas

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

Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation

Bingfeng Zhang, Jimin Xiao, Jianbo Jiao, Yunchao Wei, Yao Zhao

TPAMI 2021 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 162 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 affinity attention layer (replacing random walk) (ablation)A2GNN · PASCAL VOC 2012 train pseudo labels (box-supervised)mIoU: 71.3 -> 73.8Improved
add regularized loss L_reg (ablation)A2GNN · PASCAL VOC 2012 train pseudo labels (box-supervised)mIoU: 73.8 -> 74.9Improved
add multi-point loss L_mp (ablation)A2GNN · PASCAL VOC 2012 train pseudo labels (box-supervised)mIoU: 74.9 -> 78.1Improved
add consistency-checking (ablation)A2GNN · PASCAL VOC 2012 train pseudo labels (box-supervised)mIoU: 78.1 -> 78.8Improved
add multi-point loss to cross-entropy only (ablation)A2GNN · PASCAL VOC 2012 train pseudo labels (box-supervised)mIoU: 73.8 -> 75.9Improved
add consistency-checking to cross-entropy plus L_mp (ablation)A2GNN · PASCAL VOC 2012 train pseudo labels (box-supervised)mIoU: 75.9 -> 77.2Improved
build graph with affinity CNN instead of feature distance (ablation)A2GNN · PASCAL VOC 2012 train pseudo labels (box-supervised)mIoU: 74.7 -> 78.8Improved
use pixels of feature map as nodes instead of superpixels (ablation)A2GNN · PASCAL VOC 2012 train pseudo labels (box-supervised)mIoU: 73.3 -> 74.7Improved
use both cosine attention and edge weights in affinity attention layer vs cosine only (ablation)A2GNN · PASCAL VOC 2012 train pseudo labels (box-supervised)mIoU: 73.1 -> 78.8Improved
use both cosine attention and edge weights vs edge only (ablation)A2GNN · PASCAL VOC 2012 train pseudo labels (box-supervised)mIoU: 77.3 -> 78.8Improved
use confident seed labels M_g instead of M_F as A2GNN supervision (ablation)A2GNN · PASCAL VOC 2012 train pseudo labels (box-supervised)mIoU: 73.2 -> 78.8Improved
add L_Ar to L_Ac when using M_g seeds (ablation)affinity CNN · PASCAL VOC 2012 train pseudo labels (box-supervised)mIoU: 71.7 -> 78.8Improved

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