AI Paper Atlas

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

Adaptive Logit Adjustment Loss for Long-Tailed Visual Recognition

Yan Zhao, Weicong Chen, Xu Tan, Kai Huang, Jihong Zhu

AAAI 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training · 70 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
Replace DisAlign with ALA LossResNet-50 · ImageNet-LT testTop-1 accuracy (All): 51.3 -> 52.4Improved
Replace DisAlign with ALA LossResNeXt-50 · ImageNet-LT testTop-1 accuracy (All): 52.6 -> 53.3Improved
Replace LADE with ALA LossResNet-50 · iNaturalist 2018 validationTop-1 accuracy (All): 70.0 -> 70.7Improved
Replace DisAlign with ALA LossResNet-152 · Places-LT testTop-1 accuracy (All): 39.3 -> 40.1Improved
Add a difficulty factor to Cross Entropy (ablation)ImageNet-LT classification with ResNeXt-50 · ImageNet-LT test, Many-shotTop-1 accuracy: 65.9 -> 64.7Hurt
Add a difficulty factor to Cross Entropy (ablation)ImageNet-LT classification with ResNeXt-50 · ImageNet-LT test, Few-shotTop-1 accuracy: 7.7 -> 28.6Improved
Add a quantity factor to Cross Entropy (ablation)ImageNet-LT classification with ResNeXt-50 · ImageNet-LT test, Few-shotTop-1 accuracy: 7.7 -> 33.0Improved
Replace LDAM's quantity adjustment with the proposed quantity factor (ablation)ImageNet-LT classification with ResNeXt-50 · ImageNet-LT test, Few-shotTop-1 accuracy: 31.9 -> 33.0Improved
Combine the difficulty factor with LDAM's adjustment (ablation)ImageNet-LT classification with ResNeXt-50 · ImageNet-LT test, AllTop-1 accuracy: 51.3 -> 52.0Improved
Combine the difficulty factor with the proposed quantity factor (ablation)ImageNet-LT classification with ResNeXt-50 · ImageNet-LT test, AllTop-1 accuracy: 51.5 -> 53.3Improved

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