AI Paper Atlas

Research map / Detection and segmentation / CNN features

Robust Object Detection with Inaccurate Bounding Boxes

Chengxin Liu, Kewei Wang, Hao Lu, Zhiguo Cao, Ziming Zhang

ECCV 2022 · Detection and segmentation › CNN features · approach: Box regression and loss design · 45 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
train with the object bag instance selection loss (ablation)FasterRCNN · VOC 2007 (40% box noise)mAP@0.5: 42.5 -> 56.0Improved
train with the object bag instance selection loss (ablation)FasterRCNN · VOC 2007 (30% box noise)mAP@0.5: 60.1 -> 66.9Improved
train with the object bag instance selection loss (ablation)FasterRCNN · COCO (40% box noise)mAP@0.5: 28.9 -> 32.6Improved
add object-aware instance selection (OA-IS) (ablation)OA-MIL FasterRCNN · VOC 2007 (40% box noise)mAP@0.5: 56.0 -> 63.3Improved
add object-aware instance selection (OA-IS) (ablation)OA-MIL FasterRCNN · COCO (40% box noise)mAP@0.5: 32.6 -> 39.8Improved
add object-aware instance extension (OA-IE) (ablation)OA-MIL FasterRCNN · COCO (40% box noise)mAP@0.5: 39.8 -> 42.6Improved
add object-aware instance extension (OA-IE) (ablation)OA-MIL FasterRCNN · VOC 2007 (10% box noise)mAP@0.5: 77.2 -> 77.4No clear effect
apply OA-MIL to FasterRCNNFasterRCNN · VOC 2007 (40% box noise)mAP@0.5: 42.5 -> 63.8Improved
apply OA-MIL to RetinaNetRetinaNet · VOC 2007 (40% box noise)mAP@0.5: 45.0 -> 53.4Improved
apply OA-MIL to FasterRCNN trained on noisy GWHDFasterRCNN · GWHDVal ADA: 0.608 -> 0.639Improved
apply OA-MIL to FasterRCNN trained on clean GWHDFasterRCNN · GWHDTest ADA: 0.511 -> 0.530Improved
use Co-teaching or SD-LocNet instead of vanilla trainingFasterRCNN · VOC 2007 (40% box noise)mAP@0.5: 42.5 -> 43.7No clear effect

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