AI Paper Atlas

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

Norma: A Noise Robust Memory-Augmented Framework for Whole Slide Image Classification

Yu Bai, Bo Zhang, Zheng Zhang, Shuo Yan, Zibo Ma, Wu Liu, Xiuzhuang Zhou, Xiangyang Gong, Wendong Wang

ECCV 2024 · Label-efficient and robust learning › Noisy labels · approach: Contrastive learning on noisy data · 1 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 a global memory sink of full size (ablation)Norma · CAMELYON-16AUC: 83.2 -> 95.1Improved
add a global memory sink of full size (ablation)Norma · TCGA-LUNGAUC: 93.5 -> 96.9Improved
use full memory sink rather than half (ablation)Norma · CAMELYON-16AUC: 93.6 -> 95.1Improved
use RPEG instead of absolute positional encoding (ablation)Norma · CAMELYON-16AUC: 92.3 -> 95.1Improved
use RPEG instead of relative positional encoding (ablation)Norma · CAMELYON-16AUC: 93.9 -> 95.1Improved
keep spatial order of patches rather than random sequence (ablation)Norma · CAMELYON-16AUC: 90.1 -> 95.1Improved
add positional encoding (RPEG) (ablation)Norma · CAMELYON-16AUC: 89.7 -> 95.1Improved
use two training cycles instead of one (ablation)Norma · CAMELYON-16AUC: 92.3 -> 95.1Improved
increase cycles beyond two (ablation)Norma · CAMELYON-16AUC: 95.1 -> 94.7 (3 cycles)No clear effect
add noise detection loss Lnoise (ablation)Norma · CAMELYON-16AUC: 93.9 -> 95.1Improved
add supervised contrastive loss Lctr (ablation)Norma · CAMELYON-16AUC: 94.6 -> 95.1Improved
use learnable soft pseudo labels instead of hard argmax labels for noise detection (ablation)Norma · three WSI datasetsAUCImproved

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