AI Paper Atlas

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

Domain Generalization with Small Data

Kecheng Chen, Elena Gal, Hong Yan, Haoliang Li

IJCV 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 22 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 Bayesian layers (probabilistic embeddings) to Unet (ablation)Unet · Spinal cord GM segmentation (site2)DSC: 0.7223 -> 0.7934Improved
add Bayesian classifier on top of Bayesian layers (ablation)Unet + Bayesian layers · Spinal cord GM segmentation (site2)DSC: 0.7934 -> 0.8268Improved
add local alignment (ablation)Unet + Bayesian layers + Bayesian classifier · Spinal cord GM segmentation (site2)DSC: 0.8268 -> 0.8364Improved
add global alignment (P-MMD) (ablation)Unet + Bayesian layers + Bayesian classifier · Spinal cord GM segmentation (site2)DSC: 0.8268 -> 0.8371Improved
add both local and global alignment (ablation)Unet + Bayesian layers + Bayesian classifier · Spinal cord GM segmentation (site2)DSC: 0.8364 -> 0.8485Improved
add probabilistic embeddings (Bayesian layer) to deterministic ResNet18 baseline (ablation)SWAD baseline · Epithelium-stroma classification (avg)accuracy (%): 79.62 -> 80.63Improved
add probabilistic embeddings to deterministic baseline (ablation)SWAD baseline · Epithelium-stroma classification (NKI)accuracy (%): 74.84 -> 74.90No clear effect
replace pairwise/local-only alignment of BDIL with probabilistic framework plus global P-MMDOurs vs BDIL · Epithelium-stroma classification (NKI)accuracy (%): 71.89 -> 76.71Improved
train on 80/60/40% of source samples with the proposed method instead of BDILOurs vs BDIL · Skin lesion MSK (reduced data)accuracy: 0.6528 -> 0.6732Improved
use proposed method instead of DNA with 40/30/20 samples per classOurs vs DNA · Skin lesion MSK (few samples per class)accuracy: 0.5196 -> 0.6183Improved
replace mean embedding with kernel mean embedding (P-MMD) for alignment (ablation)Ours · Epithelium-stroma classification (NKI)accuracyImproved
increase number of Monte Carlo samples T (ablation)Ours · Epithelium-stroma classification (NKI)accuracyMixed

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