Variational Feature Disentangling for Fine-Grained Few-Shot Classification

Jingyi Xu, Hieu Le, Mingzhen Huang, ShahRukh Athar, Dimitris Samaras; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 8812-8821


Data augmentation is an intuitive step towards solving the problem of few-shot classification. However, ensuring both discriminability and diversity in the augmented samples is challenging. To address this, we propose a feature disentanglement framework that allows us to augment features with randomly sampled intra-class variations while preserving their class-discriminative features. Specifically, we disentangle a feature representation into two components: one represents the intra-class variance and the other encodes the class-discriminative information. We assume that the intra-class variance induced by variations in poses, backgrounds, or illumination conditions is shared across all classes and can be modelled via a common distribution. Then we sample features repeatedly from the learned intra-class variability distribution and add them to the class-discriminative features to get the augmented features. Such a data augmentation scheme ensures that the augmented features inherit crucial class-discriminative features while exhibiting large intra-class variance. Our method significantly outperforms the state-of-the-art methods on multiple challenging fine-grained few-shot image classification benchmarks. Code is available at:

Related Material

[pdf] [supp] [arXiv]
@InProceedings{Xu_2021_ICCV, author = {Xu, Jingyi and Le, Hieu and Huang, Mingzhen and Athar, ShahRukh and Samaras, Dimitris}, title = {Variational Feature Disentangling for Fine-Grained Few-Shot Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {8812-8821} }