AI Paper Atlas

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

UDA-Bench: Revisiting Common Assumptions in Unsupervised Domain Adaptation Using a Standardized Framework

Tarun Kalluri, Sreyas Ravichandran, Manmohan Chandraker

ECCV 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 3 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 Swin-V2-t instead of ResNet-50 backbone for source-only transfer (ablation)Source-only baseline · DomainNet (R->C)relative drop sigma_st: 45.21 -> 35.45Improved
use Swin backbone with plain source-only training instead of UDA with ResNet-50Source-only baseline · DomainNet (R->C)target accuracy: 54.5 (SOTA UDA, ResNet-50) vs 55.5 (Swin source-only)Improved
apply UDA methods on stronger backbones (Swin, DeiT) instead of ResNet-50 (ablation)UDA methods · DomainNet (R->C)relative gain over source-only: 20% (ResNet-50) -> 7% (Swin), 10% (DeiT)Hurt
apply UDA methods on Swin instead of ResNet-50 (ablation)UDA methods · OfficeHome (Ar->Pr)relative gain over source-only: 18% -> 8%Hurt
reduce unlabeled target data from 100% to 25% (ablation)UDA methods · DomainNet and VisDAtarget accuracy: <1% dropNo clear effect
double source labeled data from 50% to 100% (ablation)UDA methods · DomainNet (R->C)target accuracy: ~9% average gain vs <0.5% for doubling target unlabeled dataImproved
pre-train supervised on iNaturalist 1M instead of ImageNet 1M for birds adaptation (ablation)Plain source-only transfer · CUB->Drawingtarget accuracy: 50.2 -> 58.77Improved
pre-train supervised on Places-205 1M instead of ImageNet 1M for scene adaptation (ablation)Plain source-only transfer · GeoPlaces USA->Asiatarget accuracy: 34.55 -> 41.95Improved
use mismatched pre-training dataset (e.g. Places for birds) (ablation)UDA methods · CUB->Drawing and DomainNettarget accuracy: >10% drop in most casesHurt
add in-task pre-training on top of UDA methods (MemSAC, ToAlign) (ablation)UDA methods · CUB200target accuracy: 17.1% and 17.3% gains over ImageNet pre-training source-onlyImproved
use object-centric ImageNet pre-training instead of scene-centric Places for self-supervised (ablation)SwAV, MoCo-V3, MAE · DomainNet and CUB200target accuracy: MAE DomainNet plain 34.76 -> 38.58Improved
apply SAFN and MCD UDA methods relative to source-only baselineSAFN, MCD · Additional UDA methodsrelative gain over source-onlyHurt

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