Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classification

TL;DR

This paper introduces a novel ensemble model with spectral regularization and data augmentation techniques to improve cross-domain few-shot classification, demonstrating superior performance on multiple benchmarks.

Contribution

The paper proposes a feature transformation ensemble with batch spectral regularization and additional strategies like label propagation and data augmentation for enhanced CD-FSL performance.

Findings

Outperforms existing methods on several CD-FSL benchmarks.

Spectral regularization improves model generalization.

Ensemble and data augmentation strategies boost classification accuracy.

Abstract

In this paper, we propose a feature transformation ensemble model with batch spectral regularization for the Cross-domain few-shot learning (CD-FSL) challenge. Specifically, we proposes to construct an ensemble prediction model by performing diverse feature transformations after a feature extraction network. On each branch prediction network of the model we use a batch spectral regularization term to suppress the singular values of the feature matrix during pre-training to improve the generalization ability of the model. The proposed model can then be fine tuned in the target domain to address few-shot classification. We also further apply label propagation, entropy minimization and data augmentation to mitigate the shortage of labeled data in target domains. Experiments are conducted on a number of CD-FSL benchmark tasks with four target domains and the results demonstrate the superiority of our proposed model.