AI Paper Atlas

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

Knowledge Transfer with Simulated Inter-Image Erasing for Weakly Supervised Semantic Segmentation

Tao Chen, Xiruo Jiang, Gensheng Pei, Zeren Sun, Yucheng Wang, Yazhou Yao

ECCV 2024 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 22 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 simulated inter-image erasing (SIE) to the baseline (ablation)KTSE baseline (GPP) · PASCAL VOC 2012 train (seed)mIoU: 54.2 -> 57.1Improved
add self-supervised regularization (SSR) to the baseline (ablation)KTSE baseline (GPP) · PASCAL VOC 2012 train (seed)mIoU: 54.2 -> 57.4Improved
add multi-granularity alignment (MGA) to the baseline (ablation)KTSE baseline (GPP) · PASCAL VOC 2012 train (seed)mIoU: 54.2 -> 60.2Improved
combine SIE with SSR (ablation)KTSE · PASCAL VOC 2012 train (seed)mIoU: 57.1 -> 63.8Improved
add MGA on top of SIE and SSR (ablation)KTSE · PASCAL VOC 2012 train (seed)mIoU: 63.8 -> 67.0Improved
use global alignment on CAM features instead of rigid classification guidance (ablation)MGA · PASCAL VOC 2012 train (seed)mIoU: 55.6 -> 58.7Improved
align GPP embedding features instead of CAM features (ablation)MGA · PASCAL VOC 2012 train (seed)mIoU: 58.7 -> 54.9Hurt
add pixel-level local alignment to global alignment (ablation)MGA · PASCAL VOC 2012 train (seed)mIoU: 58.7 -> 60.2Improved
KTSE vs CutMix-based augmentation method CDAKTSE · PASCAL VOC 2012 val (ResNet)mIoU: 66.1 -> 73.0Improved
KTSE vs CutMix-based augmentation method CDAKTSE · COCO val (ResNet)mIoU: 33.2 -> 45.9Improved
SIE alone causes more under-activation for larger objects (bidirectional alignment), mitigated by SSRSIE · PASCAL VOC 2012 train (qualitative)localization mapsMixed
add IRN refinement to KTSE seedsKTSE · PASCAL VOC 2012 trainmIoU: 67.0 -> 73.8Improved

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