AI Paper Atlas

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

How Re-sampling Helps for Long-Tail Learning?

Jiang-Xin Shi, Tong Wei, Yuke Xiang, Yu-Feng Li

NeurIPS 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Classifier rebalancing and margin losses · 13 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
class-balanced re-sampling from scratch (vs uniform sampling) on semantically clean dataLeNet · MNIST-LTaccuracy (all): 65.8 -> 90.8Improved
class-balanced re-sampling from scratch (vs uniform sampling) on data with complex contextsResNet-32 · CIFAR100-LTaccuracy (all): 39.1 -> 34.1Hurt
add context-shift augmentation with context bank to class-balanced re-samplingCSA · CIFAR100-LT IR 100accuracy: 34.1 -> 45.8Improved
add context bank Q of head-class backgrounds (ablation)CSA · CIFAR100-LT IR 100accuracy: 41.2 -> 45.8Improved
use Grad-CAM instead of CAM for background extraction (ablation)CSA · CIFAR100-LT IR 100accuracy: 45.1 -> 45.8Improved
use re-sampling module only at inference instead of ensembling with uniform module (ablation)CSA · CIFAR100-LT IR 100accuracy: 43.0 -> 45.8Improved
vary selection threshold delta (0 to 0.9) (ablation)CSA · CIFAR100-LT IR 100accuracy: 44.83 -> 45.83No clear effect
increase context bank volume from 1x to 64x batch size (ablation)CSA · CIFAR100-LT IR 100accuracy: 45.83 -> 45.26Hurt
add CSA instead of CB-RS when fine-tuning SimSiam+rwSAM pretrained modelSimSiam+rwSAM · CIFAR10-LTaccuracy: 72.8 -> 75.5Improved
add mixup on top of CSACSA · CIFAR100-LT IR 100accuracy: 45.8 -> 46.6Improved
CSA vs CMO on ImageNet-LT few-shotResNet-50 · ImageNet-LTfew-shot accuracy: 20.5 -> 24.1Improved

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