AI Paper Atlas

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

Is user feedback always informative? Retrieval Latent Defending for Semi-Supervised Domain Adaptation without Source Data

Junha Song, Tae Soo Kim, Junha Kim, Gunhee Nam, Thijs Kooi, Jaegul Choo

ECCV 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 4 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 negatively biased feedback instead of random feedbackAdaMatch · DomainNet-126 (ResNet-50)top-1 accuracy: 67.6 -> 64.5Hurt
add retrieval latent defending samples to the mini-batchAdaMatch under NBF · DomainNet-126 (ResNet-50)top-1 accuracy: 64.5 -> 72.0Improved
add retrieval latent defendingFixMatch under NBF · DomainNet-126 (ResNet-50)top-1 accuracy: 63.4 -> 73.2Improved
add retrieval latent defendingAdaMatch under NBF · DomainNet-126 (ViT-S)top-1 accuracy: 73.7 -> 75.9Improved
add retrieval latent defendingPseudo-labeling under NBF · MIMIC-CXR-V2 PA to APAUROC: .7691 -> .7884Improved
add retrieval latent defendingRIPU under NBF · GTA5 to CityscapesmIoU: 54.5 -> 58.0Improved
use confident-error feedback (NBF-CE) instead of NBFPseudo-labeling · MIMIC-CXR-V2 PA to APAUROC: .7691 -> .7639Hurt
select defending samples from the same class as labeled sample (class-aware) (ablation)RLD with FreeMatch · DomainNet-126 (ResNet-50)top-1 accuracy: 74.1 -> 74.8Improved
increase filtering rate p from 0.4 to 0.8 (ablation)RLD with FreeMatch · DomainNet-126 (ResNet-50)top-1 accuracy: 74.8 -> 73.7Hurt
reduce unlabeled samples per batch (1:7 to 1:4 ratio) and add defending samples (ablation)RLD with FreeMatch · DomainNet-126 (368 feedback)top-1 accuracy: 74.2 -> 74.8Improved
add RLD to baseline under ActiveDA feedback from CLUEAdaMatch · DomainNet-126 (378 feedback)top-1 accuracy: 68.6 -> 71.5Improved
add RLD to SemiSDA methods under NBF on ViT-S versus ResNet-50 (smaller gains with ViT)SemiSDA baselines · DomainNet-126top-1 accuracy: FixMatch +9.8 (ResNet-50) vs +2.6 (ViT-S)Mixed

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