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

By Bingyu Liu, Z. Zhao, Zhenpeng Li, Jianan Jiang, Yuhong Guo, Jieping Ye. 2020

38 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

In Meta & Continual Learning

Citations in the corpus

Florence: A New Foundation Model for Computer Vision (2021, methodology): “Table 4 shows the results of adapting our model to the CDFSL benchmark, in comparison to the winner of the challenge benchmark (Liu et al., 2020), which employs ensembes and transductive learning.”