AI Paper Atlas

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

Dynamic Curriculum Learning for Imbalanced Data Classification

Yiru Wang, Weihao Gan, Jie Yang, Wei Wu, Junjie Yan

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 293 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 sampling scheduler (convex) (ablation)DeepID2 · CelebA (40 attributes)mA: 81.17 -> 86.58Improved
add triplet loss with easy anchors (ablation)DeepID2 + SS · CelebA (40 attributes)mA: 86.58 -> 87.55Improved
add loss scheduler (ablation)DeepID2 + SS + TL · CelebA (40 attributes)mA: 87.55 -> 89.05Improved
use convex instead of linear sampling scheduler (ablation)DeepID2 + SS · CelebA (40 attributes)mA: 86.36 -> 86.58Improved
use convex instead of concave sampling scheduler (ablation)DeepID2 + SS · CelebA (40 attributes)mA: 85.90 -> 86.58Improved
use convex instead of composite sampling scheduler (ablation)DeepID2 + SS · CelebA (40 attributes)mA: 86.07 -> 86.58Improved
power-transform target distribution instead of linear decrease (ablation)DeepID2 + SS · CelebA (40 attributes)mA: 85.11 -> 86.58Improved
add DCL (RAP, ratio 1:1 to 1:25) (ablation)ResNet-50 baseline · RAPmA: 79.3 -> 83.1Improved
add DCL (RAP, ratio 1:25 to 1:50) (ablation)ResNet-50 baseline · RAPmA: 68.9 -> 83.9Improved
add DCL (RAP, ratio above 1:50) (ablation)ResNet-50 baseline · RAPmA: 68.0 -> 85.5Improved
add DCL on balanced dataCross Entropy · CIFAR-100accuracy: 68.1 -> 71.5Improved
replace CRL with DCL on balanced dataCRL · CIFAR-100accuracy: 69.3 -> 71.5Improved

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