AI Paper Atlas

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

Adaptive Discriminative Regularization for Visual Classification

Qingsong Zhao, Yi Wang, Shuguang Dou, Chen Gong, Yin Wang, Cairong Zhao

IJCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training · 1 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 ADR to cross entropyResNet-50 · ImageNet-1Ktop-1 error: 23.06 -> 22.49Improved
add ADR to cross entropyResNet-101 · ImageNet-1Ktop-1 error: 21.30 -> 20.76Improved
add ADR to label smoothingViT-B/16 · ImageNet-1Ktop-1 error: 18.05 -> 17.69Improved
add ADR to CE, LS or OLSResNet-50 · Flowers-102top-1 accuracy: 90.89 -> 92.36Improved
add ADR to cross entropyAlexNet · CIFAR-10top-1 accuracy: 73.33 -> 77.07Improved
add ADR to cross entropyConvMixer · CIFAR-10top-1 accuracy: 89.79 -> 92.47Improved
add ADR on top of label smoothingAlexNet · CIFAR-10top-1 accuracy: 76.31 -> 77.75Improved
replace entropy regularizer with ADR (ablation)AlexNet CE · CIFAR-10top-1 accuracy: 74.21 -> 77.07Improved
add entropy regularizer to CE (ablation)AlexNet · CIFAR-10top-1 accuracy: 73.33 -> 74.21No clear effect
add ADR under 20% label noise (ablation)CE · CIFAR-10 noisy labelstop-1 accuracy: 72.51 -> 74.89Improved
add ADR under 40% label noise (ablation)CE · CIFAR-10 noisy labelstop-1 accuracy: 68.95 -> 70.53Improved
add ADR under 60% and 80% label noise (ablation)CE · CIFAR-10 noisy labelstop-1 accuracy: 63.45 -> 63.65No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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