AI Paper Atlas

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

Associating Inter-Image Salient Instances for Weakly Supervised Semantic Segmentation

Ruochen Fan, Qibin Hou, Ming-Ming Cheng, Gang Yu, Ralph R. Martin, Shi-Min Hu

ECCV 2018 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 104 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 graph partitioning on top of the attention module (ablation)attention-only tagging · PASCAL VOC 2012 test (VOC+SI)mIoU: 62.7 -> 64.9Improved
add graph partitioning on top of the attention module (ablation)attention-only tagging · PASCAL VOC 2012 test (VOC)mIoU: 62.0 -> 64.0Improved
add noisy-instance filtering to graph partitioning (ablation)graph partitioning · PASCAL VOC 2012 test (VOC)mIoU: 64.0 -> 64.5Improved
add noisy-instance filtering to graph partitioning (ablation)graph partitioning · PASCAL VOC 2012 test (simple ImageNet)mIoU: 62.8 -> 63.9Improved
add noisy-instance filtering to graph partitioning (ablation)graph partitioning · PASCAL VOC 2012 test (VOC+SI)mIoU: 64.9 -> 65.6Improved
replace random keyword assignment by attention-module tagging (ablation)salient instance tagging · PASCAL VOC 2012 test (VOC)mIoU: 56.4 -> 62.0Improved
add attention probability term (beta=30) to graph partitioning (ablation)graph partitioning · PASCAL VOC 2012 valmIoU: 63.2 -> 64.5Improved
increase beta too far (300 vs 30) (ablation)graph partitioning · PASCAL VOC 2012 valmIoU: 64.5 -> 62.9Hurt
filter low-confidence instances with retention ratio r=0.95 (ablation)graph partitioning · PASCAL VOC 2012 valmIoU: 63.8 -> 64.5Improved
lower retention ratio to r=0.75 (ablation)graph partitioning · PASCAL VOC 2012 valmIoU: 64.5 -> 60.9Hurt
add 24,000 simple ImageNet images to VOC trainingours ResNet101 · PASCAL VOC 2012 testmIoU: 64.5 -> 65.6Improved
use ResNet101 instead of VGG16 for the segmentation networkours (VOC) · PASCAL VOC 2012 testmIoU: 62.1 -> 64.5Improved

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