AI Paper Atlas

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

CDS: Cross-Domain Self-Supervised Pre-Training

Donghyun Kim, Kuniaki Saito, Tae-Hyun Oh, Bryan A. Plummer, Stan Sclaroff, Kate Saenko

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 56 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 cross-domain matching (replace adversarial domain classifier) (ablation)In-domain ID · CUB universal DA, open set (DANCE)mean class accuracy: 38.1 -> 55.9Improved
add cross-domain matching (replace adversarial domain classifier) (ablation)In-domain ID · CUB universal DA, closed set (DANCE)accuracy: 56.0 -> 59.0Improved
add cross-domain matching on top of in-domain instance discrimination (ablation)In-domain ID · Office D->AkNN accuracy: 61.7 -> 68.5Improved
add cross-domain matching on top of in-domain instance discrimination (ablation)In-domain ID · Office D->A, CDAN 1-shotaccuracy: 49.7 -> 66.8Improved
use in-domain instance discrimination instead of naive instance discrimination (ablation)ID · Office D->AkNN accuracy: 59.6 -> 61.7Improved
use in-domain instance discrimination instead of naive instance discrimination (ablation)ID · Office-Home cross-domain retrievalP@1: 42.2 -> 44.2Improved
apply CDS as second pre-training stage after ImageNetImageNet-pretrained ResNet-50 · CUB cross-domain retrievalP@1: 22.6 -> 40.9Improved
apply CDS as second pre-training stage after ImageNetImageNet-pretrained ResNet-50 · Office-Home cross-domain retrievalP@1: 49.9 -> 56.3Improved
apply CDS pre-trainingImageNet init + DANCE · Office-Home universal DA, partialaccuracy: 71.1 -> 69.7Hurt
apply generic SSL (ID, SimCLR, MoCo) as second stage instead of CDSImageNet init · Office-Home retrievalP@1: 49.9 -> 42.2 (ID), 48.0 (SimCLR)Hurt
apply CDS pre-training to DANCEDANCE · Office-Home open set DAH-score: 46.6 -> 68.6Improved
apply CDS pre-trainingsource-only · CUB 1-shot DAtarget accuracy: 5.1 -> 20.8Improved

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