AI Paper Atlas

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

Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination

Peng Wang, Xiao Li, Can Yaras, Zhihui Zhu, Laura Balzano, Wei Hu, Qing Qu

JMLR 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 31 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
add more projection head layers (1 to 5) during pre-training (ablation)ResNet18 pre-trained on CIFAR-100 · CIFAR-10 linear probe transfertransfer accuracyImproved
add depth by stacking extra linear or MLP layers on a 2-layer MLP (3 to 9 layers) (ablation)2-layer MLP · FashionMNIST and CIFAR-10test accuracyImproved
replace deep nonlinear MLP layers with a 5-layer linear network after a 3-layer MLP (ablation)8-layer MLP · CIFAR-10within-class compression and between-class discriminationNo clear effect

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