AI Paper Atlas

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

Feature Representation Learning for Unsupervised Cross-Domain Image Retrieval

Conghui Hu, Gim Hee Lee

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 26 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 cluster-wise contrastive loss L_CW to instance-wise loss (ablation)L_IW baseline · DomainNet averageP@50 (%): 38.14 -> 41.57Improved
add cluster-wise contrastive loss L_CW to instance-wise loss (ablation)L_IW baseline · DomainNet averageP@200 (%): 29.42 -> 32.31Improved
add self-entropy loss on clustering probabilities (ablation)v2 (L_IW + L_CW) · DomainNet averageP@50 (%): 41.57 -> 44.61Improved
add self-entropy loss on clustering probabilities (ablation)v2 (L_IW + L_CW) · DomainNet averageP@200 (%): 32.31 -> 36.01Improved
add distance-of-distance (DD) loss (ablation)v3 (without DD loss) · DomainNet averageP@50 (%): 44.61 -> 47.09Improved
add distance-of-distance (DD) loss (ablation)v3 (without DD loss) · DomainNet averageP@200 (%): 36.01 -> 39.09Improved
add DD loss on small domain-gap pair (ablation)v3 · DomainNet Real->InfographP@50 (%): 57.08 -> 57.74Improved
add DD loss on large domain-gap pair (ablation)v3 · DomainNet Real->QuickdrawP@50 (%): 33.19 -> 41.90Improved
add DD loss for Sketch->Infograph (ablation)v2 (L_IW + L_CW) · DomainNet Sketch->InfographP@50 (%): 43.81 -> 43.66Hurt
use proposed method instead of PCS on Office-HomePCS · Office-Home averageP@1 (%): 38.07 -> 40.67Improved
use proposed method instead of PCS on DomainNetPCS · DomainNet averageP@50 (%): 41.23 -> 47.09Improved

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