Ensemble Model with Batch Spectral Regularization and Data Blending for Cross-Domain Few-Shot Learning with Unlabeled Data

TL;DR

This paper introduces an ensemble approach with spectral regularization and data blending to enhance cross-domain few-shot learning, effectively utilizing unlabeled data to improve transferability and performance.

Contribution

It proposes a novel multi-branch ensemble framework with spectral regularization and a data blending method for leveraging unlabeled data in cross-domain few-shot learning.

Findings

Effective performance on CD-FSL benchmark tasks.

Improved transferability through spectral regularization.

Successful exploitation of unlabeled data for augmentation.

Abstract

In this paper, we present our proposed ensemble model with batch spectral regularization and data blending mechanisms for the Track 2 problem of the cross-domain few-shot learning (CD-FSL) challenge. We build a multi-branch ensemble framework by using diverse feature transformation matrices, while deploying batch spectral feature regularization on each branch to improve the model's transferability. Moreover, we propose a data blending method to exploit the unlabeled data and augment the sparse support set in the target domain. Our proposed model demonstrates effective performance on the CD-FSL benchmark tasks.