pith. sign in

arxiv: 1606.02819 · v4 · pith:PJEWDGRLnew · submitted 2016-06-09 · 💻 cs.CV

Low-shot Visual Recognition by Shrinking and Hallucinating Features

classification 💻 cs.CV
keywords low-shotlearningvisualclassesnovelrecognitiontechniquesability
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Growing a Brain: Fine-Tuning by Increasing Model Capacity

    cs.CV 2019-07 unverdicted novelty 5.0

    Growing CNN capacity by widening or deepening layers with normalized new units outperforms standard fine-tuning on vision benchmarks.