Ensemble Model with Batch Spectral Regularization and Data Blending for Cross-Domain Few-Shot Learning with Unlabeled Data
This addresses the problem of limited labeled data in new domains for few-shot learning applications, though it appears incremental.
The paper tackles cross-domain few-shot learning with unlabeled data by proposing an ensemble model with batch spectral regularization and data blending, achieving effective performance on benchmark tasks.
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.