# Low-shot Visual Recognition by Shrinking and Hallucinating Features

arXiv: https://arxiv.org/abs/1606.02819 · HTML: https://mlsanity.com/paper/1606.02819/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2016.

## Built on by (most cited first, 2 of 2)

- [Few Shot Activity Recognition Using Variational Inference](https://mlsanity.com/paper/2108.08990/) (2021)
- [PatchProto Networks for Few-shot Visual Anomaly Classification](https://mlsanity.com/paper/2310.04688/) (2023)

## Abstract (arXiv)

Low-shot visual learning---the ability to recognize novel object categories from very few examples---is a hallmark of human visual intelligence. Existing machine learning approaches fail to generalize in the same way. To make progress on this foundational problem, we present a low-shot learning benchmark on complex images that mimics challenges faced by recognition systems in the wild. We then propose a) representation regularization techniques, and b) techniques to hallucinate additional training examples for data-starved classes. Together, our methods improve the effectiveness of convolutional networks in low-shot learning, improving the one-shot accuracy on novel classes by 2.3x on the challenging ImageNet dataset.