AI Paper Atlas

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

iSeg: An Iterative Refinement-Based Framework for Training-Free Segmentation

Lin E. Sun, Jiale Cao, Jin Xie, Fahad Shahbaz Khan, Yanwei Pang

TPAMI 2026 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 11 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 entropy-reduced self-attention (Ent-Self) (ablation)iSeg baseline · WSSS PASCAL VOCmIoU: 68.2 -> 72.0Improved
add category-enhanced cross-attention (Cat-Cross) on top of Ent-Self (ablation)iSeg · WSSS PASCAL VOCmIoU: 72.0 -> 75.2Improved
add Ent-Self (ablation)iSeg baseline · open-vocabulary PASCAL VOCmIoU: 63.7 -> 67.1Improved
add Ent-Self (ablation)iSeg baseline · WSSS MS COCOmIoU: 40.1 -> 42.5Improved
add Ent-Self as DiffSeg post-processing (ablation)iSeg baseline · unsupervised CityscapesmIoU: 22.8 -> 25.0Improved
increase iterations from 1 to 10 (ablation)iSeg · WSSS PASCAL VOCmIoU: 71.0 -> 75.2Improved
increase iterations from 10 to 12 (ablation)iSeg · WSSS PASCAL VOCmIoU: 75.2 -> 74.9No clear effect
use updating factor 0.01 instead of 0 (ablation)iSeg · WSSS PASCAL VOCmIoU: 69.1 -> 75.2Improved
raise updating factor from 0.01 to 0.1 (ablation)iSeg · WSSS PASCAL VOCmIoU: 75.2 -> 74.1Hurt
fuse 16x16 with 32x32 cross-attention maps (ablation)iSeg · WSSS PASCAL VOCmIoU: 74.8 -> 75.2Improved
fuse earlier decoder self-attention layers (#-3) instead of last layer only (ablation)iSeg · WSSS PASCAL VOCmIoU: 75.2 -> 68.5Hurt
use time-step 100 instead of 1 (ablation)iSeg · WSSS PASCAL VOCmIoU: 73.2 -> 75.2Improved

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