Papers › Cross-Domain Few-Shot Learning via Adaptive Transformer Networks

Cross-Domain Few-Shot Learning via Adaptive Transformer Networks

25 Jan 2024arXiv:2401.13987archive 2025-07-28

Naeem Paeedeh, Mahardhika Pratama, Muhammad Anwar Ma'sum, Wolfgang Mayer, Zehong Cao, Ryszard Kowlczyk

Most few-shot learning works rely on the same domain assumption between the base and the target tasks, hindering their practical applications. This paper proposes an adaptive transformer network (ADAPTER), a simple but effective solution for cross-domain few-shot learning where there exist large domain shifts between the base task and the target task. ADAPTER is built upon the idea of bidirectional cross-attention to learn transferable features between the two domains. The proposed architecture is trained with DINO to produce diverse, and less biased features to avoid the supervision collapse problem. Furthermore, the label smoothing approach is proposed to improve the consistency and reliability of the predictions by also considering the predicted labels of the close samples in the embedding space. The performance of ADAPTER is rigorously evaluated in the BSCD-FSL benchmarks in which it outperforms prior arts with significant margins.

PaperPDFCode

Code

naeem-paeedeh/adapter officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Cross-Domain Few-ShotFew-Shot Learningcross-domain few-shot learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdapterAttentionBASEDINODense ConnectionsLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections