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

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.

References in corpus (1)

• A Broader Study of Cross-Domain Few-Shot Learning

Cited by in corpus (7)

• Dual Adaptive Representation Alignment for Cross-domain Few-shot Learning
• Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data
• Explanation-Guided Training for Cross-Domain Few-Shot Classification
• Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark
• Cross-Domain Few-Shot Classification via Adversarial Task Augmentation
• Ranking Distance Calibration for Cross-Domain Few-Shot Learning
• Domain Agnostic Few-Shot Learning For Document Intelligence