Variational Feature Disentangling for Fine-Grained Few-Shot Classification

• Main Authors: Xu, Jingyi, Le, Hieu, Huang, Mingzhen, Athar, ShahRukh, Samaras, Dimitris
• Format: Conference Proceeding
• Language: English
• Subjects: Benchmark testing; Codes; Computer vision; Image classification; Lighting; Task analysis; Transfer/Low-shot/Semi/Unsupervised Learning
• ISSN: 2380-7504
• DOI: 10.1109/ICCV48922.2021.00869

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: https://github.com/cvlab-stonybrook/vfd-iccv21