AI Paper Atlas

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

ResLT: Residual Learning for Long-tailed Recognition

Jiequan Cui, Shu Liu, Zhuotao Tian, Zhisheng Zhong, Jiaya Jia

TPAMI 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training · 161 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
use residual fusion of nested branches instead of naive summing of independent branches (ablation)ResLT · CIFAR-10-LT imbalance 0.02top-1 accuracy: 61.80 -> 83.46Improved
use residual fusion instead of vanilla CE trainingResLT · CIFAR-10-LT imbalance 0.02top-1 accuracy: 78.50 -> 83.46Improved
train with ResLT instead of cross-entropyResLT · ImageNet-LT ResNeXt-50 few-shottop-1 accuracy: 13.4 -> 35.5Improved
ResLT trades many-shot accuracy for medium and few-shotResLT · ImageNet-LT ResNeXt-50 many-shottop-1 accuracy: 67.6 -> 63.0Hurt
add strong data augmentation (mixup and autoaugment) (ablation)ResLT · ImageNet-LT ResNeXt-50top-1 accuracy: 52.9 -> 56.1Improved
add strong augmentation and ImageNet pretraining with mixup (ablation)ResLT · iNaturalist 2018top-1 accuracy: 70.2 -> 72.3Improved
add a third expert (ablation)ResLT · ImageNet-LT RIDEResNeXt-50top-1 accuracy: 56.4 -> 57.6Improved
add a third expert (ablation)ResLT · iNaturalist 2018 RIDEResNet-50top-1 accuracy: 72.1 -> 72.9Improved
increase groups from 3 to 4 (ablation)ResLT · CIFAR-100-LT imbalance 0.01top-1 accuracy: 45.34 -> 45.34No clear effect
increase groups from 3 to 5 (ablation)ResLT · CIFAR-10-LT imbalance 0.01top-1 accuracy: 80.44 -> 80.44No clear effect
use 2 groups instead of 3 (ablation)ResLT · CIFAR-10-LT imbalance 0.01top-1 accuracy: 80.44 -> 78.83Hurt
compare ResLT against grouped or separate extra convolutions (ablation)ResLT · CIFAR-LTtop-1 accuracyImproved

Later papers that compared with this method

4 later accepted papers report ResLT as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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