AI Paper Atlas

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

Feature Directions Matter: Long-Tailed Learning via Rotated Balanced Representation

Gao Peifeng, Qianqian Xu, Peisong Wen, Zhiyong Yang, Huiyang Shao, Qingming Huang

ICML 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training

Read the paper

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 fixed ETF classifier with learnable orthogonal rotation of the balanced feature (RBL) (ablation)ETF-based balanced representation learning · CIFAR100-LT (IF 50/100/200)test accuracy: +1.0, +1.4, +1.7 over FixedImproved
Learnable rotation (vs fixed ETF direction) without logit adjustment (ablation)ETF balanced representation · CIFAR100-LT (IF 200)test accuracy: 43.4 vs 41.7Improved
Fixing ETF classifier direction without logit adjustment (ablation)CE baseline with ETF classifier · CIFAR100-LT (IF 50/100/200)test accuracy: -1.3, -0.2, -1.0 vs CEHurt
Add post-hoc logit adjustment (LD) at test time (ablation)CE baseline · CIFAR100-LT (IF 200)test accuracy: +3.9 (42.7 to 46.6)Improved
Add post-hoc logit adjustment (LD) to learnable rotation model (ablation)RBL · CIFAR100-LT (IF 200)test accuracy: 43.4 to 48.9Improved
Full RBL vs Fixed ETF on CIFAR10-LTRBL · CIFAR10-LT (IF 50/100/200)test accuracy: +0.5, +0.7, +1.0Improved
Full RBL vs Fixed ETF on ImageNet-LTRBL · ImageNet-LTAll accuracy: +2.1 (51.2 to 53.3)Improved
Full RBL vs Fixed ETF on Places-LTRBL · Places-LTAll accuracy: +0.8 (38.0 to 38.8)Improved
Full RBL vs LADE on Places-LTRBL · Places-LTAll accuracy: 0.0 (38.8 vs 38.8)No clear effect
Full RBL vs best baseline LADE on ImageNet-LTRBL · ImageNet-LTAll accuracy: +0.3 (53.0 to 53.3)Improved

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