AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

One-Bit Active Query With Contrastive Pairs

Yuhang Zhang, Xiaopeng Zhang, Lingxi Xie, Jie Li, Robert C. Qiu, Hengtong Hu, Qi Tian

CVPR 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Deep active learning · 5 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 ObCP instead of VAAL at 10% labelsVGG16 active learning on ImageNet · ImageNetaccuracy: 61.3 vs 53.3Improved
Use ObCP instead of conventional one-bit supervisionCIFAR-100 one-bit active learning · CIFAR-100accuracy: 59.5% to 62.1%Improved
Use ObCP instead of conventional one-bit supervisionImageNet one-bit active learning · ImageNetaccuracy: 60.4% to 63.8%Improved
Add negative contrastive learning for incorrect predictions (ablation)ObCP · ImageNet-100top-1 accuracy: +0.8%Improved
Add the negative loss for incorrect predictions (ablation)ObCP · ImageNet-100top-1 accuracy: +2.2%Improved
Add correct queried labels as positives in the contrastive loss (ablation)ObCP · ImageNet-100top-1 accuracy: +2.5%Improved
Add correct queried labels to the supervised loss (ablation)ObCP · ImageNet-100top-1 accuracy: +6.4%Improved
Spread the query budget across four rounds instead of using it at once (ablation)ObCP · ImageNet-100accuracy: ∼6%Improved
Increase query rounds beyond the selected four (ablation)ObCP · ImageNet-100accuracyNo clear effect
Increase the initial fully labeled set size while holding the total budget fixed (ablation)ObCP · ImageNet-100accuracyNo clear effect
Use the proposed training-prediction uncertainty metric instead of Random selection (ablation)ObCP sample selection · CIFAR-100 (30% label budget)accuracy: ∼4.1%Improved
Use the proposed training-prediction uncertainty metric instead of max-confidence selection (ablation)ObCP sample selection · CIFAR-100 (30% label budget)accuracy: ∼2.3%Improved

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