AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Shape-Biased Domain Generalization via Shock Graph Embeddings

Maruthi Narayanan, Vickram Rajendran, Benjamin Kimia

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization · 17 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
use TAG convolution instead of GAT (ablation)shock graph GNN · STL-10accuracy: 56.2% -> 58%Improved
use TAG convolution instead of GCN (ablation)shock graph GNN · STL-10accuracy: 54.3% -> 58%Improved
replace ResNet-50 image CNN (DeepALL) with shock graph GNNDeepALL · PACS averageaccuracy: 35.80 -> 47.45Improved
replace ResNet-50 image CNN (DeepALL) with shock graph GNNDeepALL · VLCS averageaccuracy: 50.60 -> 57.16Improved
replace ResNet-50 image CNN (DeepALL) with shock graph GNNDeepALL · PACS Sketchaccuracy: 24.00 -> 54.15Improved
replace image CNN DG methods with shock graph GNN on color-shifted domainDeepALL · Colored MNIST rho=0.9accuracy: 10.3 -> 71.60Improved
replace image CNN with shock graph GNN on texture-confounded Art domainSelf Challenge · PACS Artaccuracy: 42.38 -> 33.26Hurt
replace image CNN with shock graph GNN on Photo domainSelf Challenge · PACS Photoaccuracy: 55.02 -> 53.23Hurt
use ImageNet-pretrained weights for image CNN methodsimage CNN DG methods · Colored MNISTaccuracyNo clear effect
replace MLDG with shock graph GNNMLDG · VLCS averageaccuracy: 53.50 -> 57.16Improved
replace Self Challenge with shock graph GNNSelf Challenge · PACS averageaccuracy: 46.95 -> 47.45Improved
replace MLDG with shock graph GNNMLDG · Colored MNIST averageaccuracy: 51.6 -> 71.94Improved

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