AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

CA2C: A Prior-Knowledge-Free Approach for Robust Label Noise Learning via Asymmetric Co-learning and Co-training

Mengmeng Sheng, Zeren Sun, Tianfei Zhou, Xiangbo Shu, Jinshan Pan, Yazhou Yao

ICCV 2025 · Label-efficient and robust learning › Noisy labels · approach: Noise-aware loss and pairwise methods · 7 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 asymmetric co-learning with paradigm deconstruction (ACPD) (ablation)CA2C · CIFAR100N Sym-20%accuracy: 35.14 -> 65.22Improved
add asymmetric co-training with cross-guidance label generation (ACLG) (ablation)CA2C · CIFAR100N Sym-20%accuracy: 65.22 -> 67.37Improved
add confidence-based re-weighting (CBRW) (ablation)CA2C · CIFAR100N Sym-20%accuracy: 67.37 -> 68.64Improved
add asymmetric co-learning with paradigm deconstruction (ACPD) (ablation)CA2C · CIFAR100N Sym-80%accuracy: 4.41 -> 28.53Improved
add asymmetric co-training with cross-guidance label generation (ACLG) (ablation)CA2C · CIFAR100N Sym-80%accuracy: 28.53 -> 35.90Improved
add confidence-based re-weighting (CBRW) (ablation)CA2C · CIFAR100N Sym-80%accuracy: 35.90 -> 40.97Improved
add asymmetric co-learning with paradigm deconstruction (ACPD) (ablation)CA2C · CIFAR100N Asym-40%accuracy: 27.29 -> 62.02Improved
add asymmetric co-training with cross-guidance label generation (ACLG) (ablation)CA2C · CIFAR100N Asym-40%accuracy: 62.02 -> 65.06Improved
add confidence-based re-weighting (CBRW) (ablation)CA2C · CIFAR100N Asym-40%accuracy: 65.06 -> 65.59Improved
add ACPD (ablation)CA2C · CIFAR80N Sym-80%accuracy: 4.20 -> 28.01Improved
add ACLG (ablation)CA2C · CIFAR80N Asym-40%accuracy: 60.39 -> 64.63Improved
set candidate label set size K to 2 (ablation)CA2C · CIFAR100N Sym-20%accuracy: highest performance at K = 2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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