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

@article{Mangla2020ChartingTR,
  title={Charting the Right Manifold: Manifold Mixup for Few-shot Learning},
  author={P. Mangla and M. Singh and Abhishek Sinha and Nupur Kumari and V. Balasubramanian and Balaji Krishnamurthy},
  journal={2020 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2020},
  pages={2207-2216}
}
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… Expand
34 Citations
Iterative label cleaning for transductive and semi-supervised few-shot learning
  • 1
  • Highly Influenced
  • PDF
Hybrid Consistency Training with Prototype Adaptation for Few-Shot Learning
  • 1
  • Highly Influenced
  • PDF
Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification
  • Yuqing Hu, V. Gripon, S. Pateux
  • Computer Science
  • 2020 25th International Conference on Pattern Recognition (ICPR)
  • 2021
  • Highly Influenced
Few Shot Learning With No Labels
  • PDF
Reinforced Attention for Few-Shot Learning and Beyond
  • 2
  • PDF
Few-Shot Classification via Feature Redistribution
Class-wise Metric Scaling for Improved Few-Shot Classification
  • Highly Influenced
  • PDF
Region Comparison Network for Interpretable Few-shot Image Classification
  • PDF
Local Propagation for Few-Shot Learning
  • PDF
...
1
2
3
4
...

References

SHOWING 1-10 OF 77 REFERENCES
Meta-Learning With Differentiable Convex Optimization
  • 314
  • Highly Influential
  • PDF
Meta-Learning for Semi-Supervised Few-Shot Classification
  • 398
  • PDF
Learning to Compare: Relation Network for Few-Shot Learning
  • 1,168
  • PDF
Optimization as a Model for Few-Shot Learning
  • 1,525
A Closer Look at Few-shot Classification
  • 449
  • Highly Influential
  • PDF
Matching Networks for One Shot Learning
  • 2,472
  • PDF
Manifold Mixup: Better Representations by Interpolating Hidden States
  • 208
  • Highly Influential
  • PDF
Meta-Learning with Latent Embedding Optimization
  • 458
  • Highly Influential
  • PDF
Meta-learning with differentiable closed-form solvers
  • 242
  • Highly Influential
  • PDF
Delta-encoder: an effective sample synthesis method for few-shot object recognition
  • 109
  • PDF
...
1
2
3
4
5
...