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

Mangla, Puneet and Singh, Mayank and Sinha, Abhishek and Kumari, Nupur and Balasubramanian, Vineeth N and Krishnamurthy, Balaji (2020) Charting the Right Manifold: Manifold Mixup for Few-shot Learning. In: Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020, 1 March 2020 - 5 March 2020.

Full text not available from this repository. (Request a copy)


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 general-purpose 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, mini-ImageNet and tiered-ImageNet 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:
IITH CreatorsORCiD
Balasubramanian, Vineeth NUNSPECIFIED
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Cross-domain; Data distribution; Learning performance; Model parameters; Regularization technique; Relevant features; State of the art
Subjects: Computer science
Divisions: Department of Computer Science & Engineering
Depositing User: . LibTrainee 2021
Date Deposited: 31 Jul 2021 11:23
Last Modified: 31 Jul 2021 11:23
Publisher URL:
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 8612 Statistics for this ePrint Item