AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

ETAB: A Benchmark Suite for Visual Representation Learning in Echocardiography

Ahmed Alaa, Anthony Philippakis, David Sontag

NeurIPS 2022 · Vision-language and multimodal › Human and embodied modeling · approach: Medical vision-language models · 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
Pre-train on source task instead of training from scratch (ablation)SegFormer head with ResNet-50 · a0-A4-E/a0-A4-C and a0-A4-C/a0-A2-CDICE scoreImproved
Pre-train on source task instead of training from scratch (ablation)SegFormer head with ResNet-50 · a0-A4-C/a2-A4-CDICE scoreNo clear effect
Label shift between source and target (a0-A4-C/a1-A4-C, a0-A4-C/a2-A4-C) vs data set or view shiftsegmentation heads with ResNet-50 · transfer benchmarksDICE score: 0.540 vs 0.885Hurt
Switch head from U-Net to DeepLabV3ResNet-50 encoder · a0-A4-C/a2-A4-CDICE score: 0.540 -> 0.666Improved
Switch head from U-Net to LinknetResNet-50 encoder · a0-A4-C/a1-A4-CDICE score: 0.729 -> 0.481Hurt
Switch head from U-Net to U-Net++ResNet-50 encoder · a0-A4-E/a0-A4-CDICE score: 0.909 -> 0.804Hurt
Switch head from U-Net to PSPNetResNet-50 encoder · a0-A4-E/a2-A4-CDICE score: 0.634 -> 0.707Improved
Different segmentation head across benchmarksResNet-50 encoder · six transfer benchmarksDICE scoreMixed
Use CNN backbones instead of ViT backbones (MiT, PoolFormer)ETAB backbone evaluation · ETAB benchmarkETAB score: 0.689 vs 0.653Improved
Fully finetune ResNet-50 instead of freezing ImageNet-1K weights (ablation)ResNet-50 · ETAB benchmarkETAB score: 0.689 -> 0.769Improved
Fully finetune MiT-B2 instead of freezing ImageNet-1K weights (ablation)MiT-B2 · ETAB benchmarkETAB score: 0.653 -> 0.691Improved
Fully finetune the entire backbone instead of tuning the head only (ablation)backbone models · ETAB benchmarkETAB scoreNo clear effect

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