AI Paper Atlas

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

No One Left Behind: Improving the Worst Categories in Long-Tailed Learning

Yingxiao Du, Jianxin Wu

CVPR 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training · 18 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
Fine-tune PaCo's classifier with GMLPaCo · CIFAR100-LT (imbalance ratio 100)Harmonic Mean: 36.42 -> 39.20Improved
Fine-tune PaCo's classifier with GMLPaCo · CIFAR100-LT (imbalance ratio 100)Lowest Recall: 5.00 -> 9.00Improved
Ensemble the original and GML-fine-tuned classifiersPaCo + GML · CIFAR100-LT (imbalance ratio 100)Harmonic Mean: 39.20 -> 41.02Improved
Ensemble the original and GML-fine-tuned classifiersPaCo + GML · CIFAR100-LT (imbalance ratio 100)Accuracy: 50.53 -> 49.82Hurt
Fine-tune PaCo's classifier with GMLPaCo · ImageNet-LTHarmonic Mean: 21.79 -> 43.71Improved
Fine-tune PaCo's classifier with GMLPaCo · ImageNet-LTLowest Recall: 0.00 -> 2.00Improved
Fine-tune MiSLAS's classifier with GML and label-aware smoothingMiSLAS · Places-LTHarmonic Mean: 28.97 -> 29.98Improved
Remove re-weighting from GML (ablation)CE + GML · CIFAR100-LT (imbalance ratio 100)Harmonic Mean: 31.26 -> 5.11Hurt
Replace GML re-weighting with re-sampling (ablation)CE + GML · CIFAR100-LT (imbalance ratio 100)Harmonic Mean: 31.26 -> 23.05Hurt
Use cross-entropy with re-weighting instead of GML for fine-tuning (ablation)CE fine-tuning · CIFAR100-LT (imbalance ratio 100)Harmonic Mean: 31.26 -> 27.55Hurt
Use cross-entropy with re-sampling instead of GML for fine-tuning (ablation)CE fine-tuning · CIFAR100-LT (imbalance ratio 100)Lowest Recall: 6.00 -> 2.00Hurt
Train from scratch with GML rather than attaching it to a pretrained model (ablation)GML · CIFAR100-LT (imbalance ratio 100)Harmonic Mean: 31.26 -> 30.86; 39.20 -> 30.86Mixed

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