A Transductive Multi-Head Model for Cross-Domain Few-Shot Learning

TL;DR

This paper introduces TMHFS, a novel cross-domain few-shot learning method combining multiple training heads and semantic information, significantly improving performance across various domains.

Contribution

The paper proposes a new multi-head model with semantic classification for cross-domain few-shot learning, extending existing methods with a novel prediction head and data augmentation techniques.

Findings

Outperforms strong baselines on four target domains

Effective use of semantic information improves accuracy

Data augmentation enhances model robustness

Abstract

In this paper, we present a new method, Transductive Multi-Head Few-Shot learning (TMHFS), to address the Cross-Domain Few-Shot Learning (CD-FSL) challenge. The TMHFS method extends the Meta-Confidence Transduction (MCT) and Dense Feature-Matching Networks (DFMN) method [2] by introducing a new prediction head, i.e, an instance-wise global classification network based on semantic information, after the common feature embedding network. We train the embedding network with the multiple heads, i.e,, the MCT loss, the DFMN loss and the semantic classifier loss, simultaneously in the source domain. For the few-shot learning in the target domain, we first perform fine-tuning on the embedding network with only the semantic global classifier and the support instances, and then use the MCT part to predict labels of the query set with the fine-tuned embedding network. Moreover, we further exploit data augmentation techniques during the fine-tuning and test stages to improve the prediction performance. The experimental results demonstrate that the proposed methods greatly outperform the strong baseline, fine-tuning, on four different target domains.