Charting the Right Manifold: Manifold Mixup for Few-shot Learning

Mangla, Puneet and Balasubramanian, Vineeth N and Singh, Mayank and et al, . (2019) Charting the Right Manifold: Manifold Mixup for Few-shot Learning. arXiv.org.

Preview

Text
1907.12087.pdf
Download (758kB) | Preview

Abstract

Few-shot learning algorithms aim to learn model parameters capable of adapting to unseen classes with the help of only a few labeled examples. A recent regularization technique - Manifold Mixup focuses on learning a generalpurpose representation, robust to small changes in the data distribution. Since the goal of few-shot learning is closely linked to robust representation learning, we study Manifold Mixup in this problem setting. Self-supervised learning is another technique that learns semantically meaningful features, using only the inherent structure of the data. This work investigates the role of learning relevant feature manifold for few-shot tasks using self-supervision and regularization techniques. We observe that regularizing the feature manifold, enriched via self-supervised techniques, with Manifold Mixup significantly improves few-shot learning performance. We show that our proposed method S2M2 beats the current state-of-the-art accuracy on standard few-shot learning datasets like CIFAR-FS, CUB and miniImageNet by 3 − 8%. Through extensive experimentation, we show that the features learned using our approach generalize to complex few-shot evaluation tasks, cross-domain scenarios and are robust against slight changes to data distribution.

[error in script]

IITH Creators: