AI Paper Atlas

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

DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classification

Wenhui Zhu, Xiwen Chen, Peijie Qiu, Aristeidis Sotiras, Abolfazl Razi, Yalin Wang

ECCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 39 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 positive instance alignment module to global vectors (ablation)DGR-MIL · CAMELYON16AUC: 0.922 -> 0.944Improved
add DPP diversity loss on top of positive alignment (ablation)DGR-MIL · CAMELYON16AUC: 0.944 -> 0.957Improved
add DPP diversity loss on top of positive alignment (ablation)DGR-MIL · TCGA-NSCLCAUC: 0.956 -> 0.963Improved
add tokenized global vector (ablation)DGR-MIL · CAMELYON16AUC: 0.935 -> 0.957Improved
add tokenized global vector (ablation)DGR-MIL · TCGA-NSCLCAUC: 0.957 -> 0.963Improved
global vectors via cross-attention only, without learning strategies (ablation)DGR-MIL · CAMELYON16 / TCGA-NSCLCAUC: 0.922 and 0.928 baselineImproved
increase number of global vectors K beyond optimum (K=5 CAMELYON16, K=3 TCGA)DGR-MIL · CAMELYON16 / TCGA-NSCLCperformanceHurt
increase loss balance weights lambda_tri and lambda_div to 0.5 or 1.0DGR-MIL · CAMELYON16classification performanceHurt
reduce loss balance weights to 0.01DGR-MIL · CAMELYON16performanceHurt
use DGR-MIL instead of DTFD-MIL (AFS) with ResNet-50 featuresMIL aggregation · CAMELYON16accuracy: 0.908 -> 0.917Improved

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