AI Paper Atlas

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

Pro2SAM: Mask Prompt to SAM with Grid Points for Weakly Supervised Object Localization

Xi Yang, Songsong Duan, Nannan Wang, Xinbo Gao

ECCV 2024 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 3 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
replace self-attention map with global tokens in GTFormer (ablation)GTFormer · ILSVRCTop-1 Loc: 43.0 -> 60.2Improved
add global-token attention (GTA) (ablation)GTFormer · ILSVRCTop-1 Loc: 51.1 -> 60.2Improved
use 4 global tokens instead of 1 (ablation)GTFormer · ILSVRCTop-1 Loc: 59.4 -> 60.2Improved
use 16 global tokens instead of 4 (ablation)GTFormer · ILSVRCTop-1 Loc: 60.2 -> 41.3Hurt
set loss weights mu:lambda to 1:0.5 instead of 1:1 (ablation)GTFormer · ILSVRCTop-1 Loc: 43.6 -> 60.2Improved
mask matching instead of bounding box matching of SAM masks (ablation)Pro2SAM · ILSVRCIOU50: 53.3 -> 77.8Improved
mask matching instead of combined mask and bbox matching (ablation)Pro2SAM · ILSVRCIOU90: 40.3 -> 45.9Improved
add SAM grid-point mask matching on top of GTFormerGTFormer · ILSVRCTop-1 Loc: 60.2 -> 66.85Improved
add SAM on top of GTFormerGTFormer · CUB-200-2011GT-Known: 98.48 -> 95.67Hurt
add SAM on top of GTFormer, fine-grained localizationGTFormer · CUB-200-2011MaxBoxAccV2 IOU90: 8.70 -> 48.43Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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