AI Paper Atlas

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

SCL-WC: Cross-Slide Contrastive Learning for Weakly-Supervised Whole-Slide Image Classification

Xiyue Wang, Jinxi Xiang, Jun Zhang, Sen Yang, Zhongyi Yang, Ming-Hui Wang, Jing Zhang, Yang Wei, Junzhou Huang, Xiao Han

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 8 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
SSL histopathology-pretrained extractor instead of ImageNet (ablation)SCL-WC · Camelyon16AUC: 0.8730 -> 0.9080Improved
SSL histopathology-pretrained extractor instead of ImageNet (ablation)SCL-WC · BRACSAUC: 0.8114 -> 0.8335Improved
add positive-negative-aware loss (PNM) (ablation)SCL-WC · Camelyon16AUC: 0.9080 -> 0.9190Improved
add positive-negative-aware loss (PNM) (ablation)SCL-WC · BRACSAUC: 0.8335 -> 0.8403Improved
add WSCL without hard negatives (ablation)SCL-WC · Camelyon16AUC: 0.9190 -> 0.9330Improved
add hard negative samples to WSCL (ablation)SCL-WC · Camelyon16AUC: 0.9330 -> 0.9566Improved
add hard negative samples to WSCL (ablation)SCL-WC · BRACSAUC: 0.8512 -> 0.8650Improved
our aggregator instead of CLAM aggregator (ablation)SCL-WC · TCGA-CRC-DX (own extractor)AUC: 0.8530 -> 0.8954Improved
our extractor instead of DINO-ViT (ablation)SCL-WC · TCGA-CRC-DXAUC: 0.8246 -> 0.8954Improved
our aggregator instead of CLAM aggregatorSCL-WC · BRACS (ImageNet extractor)AUC: 0.8158 -> 0.8446Improved
SCL-WC versus TransMILSCL-WC · Camelyon16AUC: 0.9337 -> 0.9566Improved
SCL-WC versus CLAMSCL-WC · PANDAACC: 0.8874 -> 0.9194Improved

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