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

By Puneet Mangla, Mayank Kumar Singh, Abhishek Sinha, Nupur Kumari, Vineeth Nallure Balasubramanian, Balaji Krishnamurthy. IEEE Workshop/Winter Conference on Applications of Computer Vision, 2019

386 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/ccbe37b5c4d8a5687153df6fedbb44d6f1c46d7d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities (2022, neutral): “S2M2R [239] WACV’20 Embedding ResNet-18 64.”
Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning (2021, methodology): “To address this, inspired by the effectiveness of mixup for helping learn a smoother decision boundary [42, 54], we further use the mixed data from the generated hard sample pair set (denoted by B ) for classiﬁer training: In this way, Core-tuning is able to learn a smoother classiﬁer that is far…”
Bowtie Networks: Generative Modeling for Joint Few-Shot Recognition and Novel-View Synthesis (2020, result): “Note that while conducting comparisons with other view synthesis models (such as [42, 34, 19, 28, 12, 43, 40]) and few-shot recognition models (such as [2, 16, 6]) are interesting, this is not the main focus of our paper.”
DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning (2020, methodology): “Following [120], we add a self-supervised auxiliary learning task during backbone pre-training and observe its”
Leveraging the Feature Distribution in Transfer-based Few-Shot Learning (2020, methodology): “g novel classes. Among these wclasses, slabelled examples and qunlabelled examples per class are uniformly drawn at random to form D novel. In our settings, the WRN and ResNet18 are trained following [17], while we train the DenseNet121 by following [34]. In order to better segregate between feature”
Free Lunch for Few-shot Learning: Distribution Calibration (2021, methodology): “56 64.38 ± 0.63 ( ↑ 9.850 ) WRN28 + Rotation Loss (Mangla et al., 2020) 56 .”
Compositional Few-Shot Recognition with Primitive Discovery and Enhancing (2020, methodology): “Therefore, inspired by current works [19, 31, 37] on self-supervised learning, we propose to use the split-based self-supervised mechanism for FSL, where we split the input image horizontally and vertically, perm the splits, and ask the model to recognize which perms are applied to them.”
Negative Margin Matters: Understanding Margin in Few-shot Classification (2020, methodology): “Hence, learning to generalize the knowledge in base classes (with sufficient annotated examples) to novel classes (with a few labeled examples), also known as few-shot learning, has attracted more and more attention [3,19,25,7,46,43,9,37,44,36,35,10].”