AI Paper Atlas

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

Object-Aware Instance Labeling for Weakly Supervised Object Detection

Satoshi Kosugi, Toshihiko Yamasaki, Kiyoharu Aizawa

ICCV 2019 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 62 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 CAP labeling to OICR (ablation)OICR · PASCAL VOC 2007mAP: 41.2 -> 45.6Improved
add CAP labeling to OICR (ablation)OICR · PASCAL VOC 2007CorLoc: 60.6 -> 66.6Improved
add SRN labeling to OICR (ablation)OICR · PASCAL VOC 2007mAP: 41.2 -> 45.1Improved
add SRN labeling to OICR (ablation)OICR · PASCAL VOC 2007CorLoc: 60.6 -> 63.4Improved
add SRN labeling on top of CAP labeling (ablation)CAP labeling · PASCAL VOC 2007mAP: 45.6 -> 47.6Improved
add CAP labeling on top of SRN labeling (ablation)SRN labeling · PASCAL VOC 2007mAP: 45.1 -> 47.6Improved
add SRN labeling on top of CAP labeling (ablation)CAP labeling · PASCAL VOC 2007CorLoc: 66.6 -> 66.7No clear effect
use context classification instead of simple mask-out (ablation)Ours · PASCAL VOC 2007mAP: 47.1 -> 47.6Improved
use context classification instead of simple mask-out (ablation)Ours · PASCAL VOC 2007CorLoc: 64.9 -> 66.7Improved
apply PGE pseudo ground-truth excavation to Ours + FRCNNOurs + FRCNN · PASCAL VOC 2007 test (Fast R-CNN retrained)mAP: 51.4 -> 52.1 on VOC 2007; 48.1 -> 47.9 on VOC 2012Mixed
Train Fast R-CNN on our localization instead of OICR with PGEFast R-CNN · PASCAL VOC 2012 test (Fast R-CNN retrained)mAP: 47.3 -> 48.1Improved

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