AI Paper Atlas

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

SRasP: Self-Reorientation Adversarial Style Perturbation for Cross-Domain Few-Shot Learning

Wenqian Li, Pengfei Fang, Hui Xue

TPAMI 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 0 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 Self-Reorientation gradient ensemble to baseline (ablation)baseline · CD-FSL 1-shotaverage accuracy: 45.56 -> 46.94Improved
add Self-Reorientation gradient ensemble to baseline (ablation)baseline · CD-FSL 5-shotaverage accuracy: 62.07 -> 62.81Improved
add semantic consistency loss L_con to SR (ablation)SRasP · CD-FSL 1-shotaverage accuracy: 46.94 -> 48.67Improved
add CDTO loss to SR (ablation)SRasP · CD-FSL 1-shotaverage accuracy: 46.94 -> 47.15Improved
use full SR + CDTO + L_con (ablation)SRasP · CD-FSL 1-shotaverage accuracy: 48.67 -> 50.24Improved
use incoherent crop mining instead of random crops (ablation)SRasP · CD-FSL 1-shotaverage accuracy: 49.49 -> 50.24Improved
use incoherent crop mining instead of concept crops (ablation)SRasP · CD-FSL 5-shotaverage accuracy: 65.24 -> 65.78Improved
set reorientation factor xi=0.1 instead of 0.01 (ablation)SRasP · CD-FSL 1-shotaverage accuracy: 49.49 -> 50.24Improved
set reorientation factor xi=1 instead of 0.1 (ablation)SRasP · CD-FSL 1-shotaverage accuracy: 50.24 -> 49.58Hurt
set trade-off lambda=0.2 instead of 0 (ablation)SRasP · CD-FSL 1-shotaverage accuracy: 49.69 -> 50.24Improved
increase lambda from 0.2 to 1 (ablation)SRasP · CD-FSL 5-shotaverage accuracy: 65.78 -> 64.50Hurt
use different kappa1 and kappa2 instead of the same (ablation)SRasP · CD-FSL 1-shotaverage accuracy: 49.30 -> 50.24Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

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