AI Paper Atlas

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

Box-based Refinement for Weakly Supervised and Unsupervised Localization Tasks

Eyal Gomel, Tal Shaharbany, Lior Wolf

ICCV 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 5 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 box-union loss with probability 0.5 when refining g (ablation)refined phrase grounding network · Flickr30K, MS-COCO trained, bbox accuracybbox accuracy (%): 28.74 -> 47.26Improved
add the original g training losses alongside the detector loss (ablation)refined phrase grounding network · Flickr30K, MS-COCO trained, pointing accuracypointing accuracy (%): 68.47 -> 77.19Improved
predict k=10 boxes instead of k=1 in phrase grounding (ablation)refined phrase grounding network · Flickr30K, MS-COCO trained, bbox accuracybbox accuracy (%): 32.35 -> 47.26Improved
refine g with detector-based lossWWbL phrase grounding · Flickr30K, MS-COCO trained, bbox accuracybbox accuracy (%): 35.75 -> 47.26Improved
add regularization terms to detector loss in object discovery (ablation)refined DINO with LOST · VOC07 CorLocCorLoc (%): 61.72 -> 62.0Improved
use k=1 box instead of k=10 in object discovery (ablation)refined DINO with LOST · VOC07 CorLocCorLoc (%): 62.0 -> 62.54Improved
vary k from 1 to 15 in object discovery (ablation)refined DINO with LOST · MS-COCO20K CorLocCorLoc (%): 52.00 (k=1), 51.98 (k=10), 50.60 (k=15)No clear effect
refine DINO with detector loss on MOVE boxesMOVE · VOC07 CorLocCorLoc (%): 76.0 -> 77.5Improved
refine DINO with detector loss on TokenCut boxesTokenCut · VOC07 CorLocCorLoc (%): 68.8 -> 69.0No clear effect
refine DINO with detector loss on LOST boxesLOST · VOC07 CorLocCorLoc (%): 61.9 -> 62.0No clear effect
add refinement on top of MOVE + CADMOVE + CAD · VOC07 CorLocCorLoc (%): 77.1 -> 78.7Improved

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