SelectNAdapt: Support Set Selection for Few-Shot Domain Adaptation

TL;DR

SelectNAdapt introduces a novel method for selecting the most representative target domain samples for few-shot adaptation, improving model performance over random selection by leveraging self-supervised features and clustering.

Contribution

The paper proposes a new algorithm, SelectNAdapt, for curated support set selection in few-shot domain adaptation using self-supervised features and clustering, enhancing adaptation effectiveness.

Findings

Outperforms standard random selection in benchmarks

Effective clustering improves sample representativeness

Utilizes pseudo-labels for practical applicability

Abstract

Generalisation of deep neural networks becomes vulnerable when distribution shifts are encountered between train (source) and test (target) domain data. Few-shot domain adaptation mitigates this issue by adapting deep neural networks pre-trained on the source domain to the target domain using a randomly selected and annotated support set from the target domain. This paper argues that randomly selecting the support set can be further improved for effectively adapting the pre-trained source models to the target domain. Alternatively, we propose SelectNAdapt, an algorithm to curate the selection of the target domain samples, which are then annotated and included in the support set. In particular, for the K-shot adaptation problem, we first leverage self-supervision to learn features of the target domain data. Then, we propose a per-class clustering scheme of the learned target domain features and select K representative target samples using a distance-based scoring function. Finally, we bring our selection setup towards a practical ground by relying on pseudo-labels for clustering semantically similar target domain samples. Our experiments show promising results on three few-shot domain adaptation benchmarks for image recognition compared to related approaches and the standard random selection.