Journal
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
Volume -, Issue -, Pages 8792-8801Publisher
IEEE
DOI: 10.1109/ICCV48922.2021.00869
Keywords
-
Funding
- Zebra Technologies
- Partner University Fund
- SUNY2020 ITSC
Ask authors/readers for more resources
The study introduces a feature disentanglement framework to augment samples in few-shot classification while preserving their class-discriminative features. By separating the feature representation into intra-class variance and class-discriminative information, the framework effectively enhances features.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available