AI Paper Atlas

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

Semi-Supervised Object Detection via Virtual Category Learning

Changrui Chen, Kurt Debattista, Jungong Han

ECCV 2022 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection

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 VC learning instead of discarding confusing samples (ablation)Unbiased Teacher · MS COCO 1% labels (ablation, small batch)mAP: 19.37 -> 20.81Improved
add VC learning instead of keeping all potential labels (ablation)Unbiased Teacher · MS COCO 1% labels (ablation, small batch)mAP: 19.36 -> 20.81Improved
add VC learning to the baseline (ablation)Unbiased Teacher · MS COCO 1% labels (ablation, small batch)mAP: 20.00 -> 20.81Improved
add Reg* loss on top of VC loss (ablation)VC learning · MS COCO 1% labels (ablation, small batch)mAP: 20.81 -> 20.94Improved
use cross-model verification instead of temporal stability to build the PC set (ablation)VC learning · MS COCO 1% labels (ablation, small batch)mAP: 20.81 -> 20.96Improved
add co-training without VC (ablation)Unbiased Teacher · MS COCO 1% labels (ablation, small batch)mAP: 20.00 -> 20.53Improved
flip the input for the virtual weight instead of no augmentation (ablation)VC learning · MS COCO 1% labels (ablation, small batch)mAP: 20.80 -> 20.81No clear effect
use strong augmentation for the virtual weight (ablation)VC learning · MS COCO 1% labels (ablation, small batch)mAP: 20.81 -> 20.70Hurt
set scaling factor 3.5 instead of 2.5 or 4.5 (ablation)VC learning · MS COCO 1% labels (ablation, small batch)mAP: 20.63 / 20.65 -> 20.81Improved
raise location quality threshold t_loc from 0.05 to 0.1 (ablation)VC learning + Reg* · MS COCO 1% labels (ablation, small batch)mAP: 20.94 -> 20.31Hurt
add VC learning plus Soft Teacher tricksUnbiased Teacher · MS COCO 0.5% labelsmAP: 16.94 -> 19.46Improved
add VC learning with identical settingsUnbiased Teacher · MS COCO 1% labelsmAP: 20.75 -> 21.61Improved

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