AI Paper Atlas

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

Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed Learning

Binwu Wang, Pengkun Wang, Wei Xu, Xu Wang, Yudong Zhang, Kun Wang, Yang Wang

ICLR 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Classifier rebalancing and margin losses

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Rethinks data augmentation for deep long-tailed learning, proposing a method that addresses both head-tail imbalance and intra-class diversity in one stroke.

Problem

Deep models trained on long-tailed class distributions become biased toward head classes, hurting inter-class fairness.

Approach

Rethinks data augmentation as a way to address long-tailed learning, aiming to kill two birds with one stone (class imbalance and sample diversity) rather than relying on sophisticated sampling or loss re-weighting. Details beyond the abstract are not available.

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