Journal
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
Volume -, Issue -, Pages 3037-3046Publisher
IEEE
DOI: 10.1109/ICCV.2017.328
Keywords
-
Ask authors/readers for more resources
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 lowshot learning benchmark on complex images that mimics challenges faced by recognition systems in the wild. We then propose (1) representation regularization techniques, and (2) 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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available