AI Paper Atlas

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

TITAN: Query-Token based Domain Adaptive Adversarial Learning

Tajamul Ashraf, Janibul Bashir

ICCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain 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
add query-based adversarial alignment on encoder and decoder (ablation)FocalNet-DINO student-teacher baseline · C2FmAP: 35.2 -> 40.8Improved
add token-wise adversarial alignment on encoder and decoder (ablation)FocalNet-DINO student-teacher baseline · C2FmAP: 35.2 -> 39.7Improved
combine query-based and token-wise adversarial learning on the encoder (ablation)FocalNet-DINO · C2FmAP: 38.5 -> 47.1Improved
combine query-based and token-wise adversarial learning on the decoder (ablation)FocalNet-DINO · C2FmAP: 37.9 -> 45.6Improved
add variance-based target division into easy and hard subsets (ablation)TITAN with all adversarial modules · C2FmAP: 47.1 -> 51.2Improved
apply TITAN versus best prior source-free methodTITAN · C2FmAP: 40.9 -> 52.2Improved
apply TITAN versus UDA method PT on K2CTITAN · K2CCar AP: 55.1 -> 53.2No clear effect
apply TITAN on mammography adaptation versus best source-free baselineTITAN · RSNA-BSD1K to INBreastRecall at 0.3 FPI: 0.25 -> 0.78Improved
use simple three-layer MLP discriminatorsTITAN adversarial modules · generalization analysisgeneralization boundImproved

Later papers that compared with this method

2 later accepted papers report TITAN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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