AI Paper Atlas

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

Noise-Aware Fully Webly Supervised Object Detection

Yunhang Shen, Rongrong Ji, Zhiwei Chen, Xiaopeng Hong, Feng Zheng, Jianzhuang Liu, Mingliang Xu, Qi Tian

CVPR 2020 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 38 citations (OpenAlex)

Check 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
Use the noise-aware framework rather than direct WSDDN training on web imagesVGG16 detector · PASCAL VOC 2007 testmAP: 27.6 -> 35.1Improved
Add a residual detection head (ablation)Webly supervised VGG16 detector · PASCAL VOC 2007 testmAP: 27.6 -> 29.8Improved
Use original entropy weighting for background labels (ablation)Residual detection model · PASCAL VOC 2007 testmAP: 27.6 -> 30.7Improved
Use spatially-sensitive entropy rather than the original entropy weighting (ablation)Residual detection model · PASCAL VOC 2007 testmAP: 30.7 -> 33.4Improved
Apply SSE to foreground as well as background categories (ablation)Residual detection model with SSE · PASCAL VOC 2007 testmAP: 33.4 -> 33.6Improved
Add bagging-mixup using two images per bag (ablation)Residual detection model with SSE · PASCAL VOC 2007 testmAP: 33.4 -> 35.1Improved
Increase bagging-mixup bag size from 2 to 3 images (ablation)Residual detection model with SSE and bagging-mixup · PASCAL VOC 2007 testmAP: 35.1 -> 35.2No clear effect
Increase bagging-mixup bag size from 2 to 4 images (ablation)Residual detection model with SSE and bagging-mixup · PASCAL VOC 2007 testmAP: 35.1 -> 35.1No clear effect
Train on Flickr-COCO with the noise-aware method rather than WSDDNVGG16 detector · MS COCO minivalAP0.5: 7.0 -> 10.6Improved

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