Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classification
This addresses the challenge of few-shot learning when source and target domains differ, with incremental improvements to existing methods.
The paper tackles cross-domain few-shot classification by proposing a feature transformation ensemble model with batch spectral regularization, achieving superior results on benchmark tasks across four target domains.
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.