AI Paper Atlas

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

Cross-token Guidance Transformer for Weakly Supervised Object Localization

Zhiwei Chen, Yiran Nie, Ruize Han, Qinqin Zhou

ECCV 2026 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 0 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 Attention Regulation Module to vanilla (ablation)vanilla DeiT-S location-token transformer · ILSVRC valGT-known Loc: 69.10 -> 70.91Improved
add Filter Regulation Module to vanilla (ablation)vanilla DeiT-S location-token transformer · ILSVRC valTop-1 Loc: 56.86 -> 58.22Improved
add FRM on top of ARM (ablation)ARM-only model · ILSVRC valTop-1 Loc: 58.57 -> 60.35Improved
add ARM on top of FRM (ablation)FRM-only model · ILSVRC valGT-known Loc: 70.58 -> 73.33Improved
add ARM to vanilla (ablation)vanilla · CUB-200-2011Top-1 Loc: 76.25 -> 79.43Improved
add FRM to vanilla (ablation)vanilla · CUB-200-2011Top-1 Loc: 76.25 -> 78.36Improved
add both ARM and FRM (ablation)vanilla · CUB-200-2011GT-known Loc: 91.77 -> 98.68Improved
add both ARM and FRM (ablation)vanilla · ILSVRC valTop-1 Loc: 56.86 -> 60.35Improved
use lambda 0.45 instead of 0.40/0.55 (ablation)CGTR · CUB-200-2011Top-1 Loc: 80.81 -> 81.80Mixed
vary lambda 0.40 to 0.55 (ablation)CGTR · ILSVRC valTop-1 Loc: 60.28 -> 60.35No clear effect
use larger pooling kernel k in FRM (ablation)CGTR · ILSVRC valLoc accuracyHurt
set xi to 0.37 (ablation)CGTR · ILSVRC valLoc accuracyImproved

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