Low-Shot Learning from Imaginary Data

Humans can quickly learn new visual concepts, perhaps because they can easily visualize or imagine what novel objects look like from different views. Incorporating this ability to hallucinate novel instances of new concepts might help machine vision systems perform better low-shot learning, i.e., le...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 7278 - 7286
Main Authors Wang, Yu-Xiong, Girshick, Ross, Hebert, Martial, Hariharan, Bharath
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Data visualization
Feature extraction
Machine vision
Strain
Task analysis
Training
Visualization
Online AccessGet full text

Cover

More Information
Summary:Humans can quickly learn new visual concepts, perhaps because they can easily visualize or imagine what novel objects look like from different views. Incorporating this ability to hallucinate novel instances of new concepts might help machine vision systems perform better low-shot learning, i.e., learning concepts from few examples. We present a novel approach to low-shot learning that uses this idea. Our approach builds on recent progress in meta-learning ("learning to learn") by combining a meta-learner with a "hallucinator" that produces additional training examples, and optimizing both models jointly. Our hallucinator can be incorporated into a variety of meta-learners and provides significant gains: up to a 6 point boost in classification accuracy when only a single training example is available, yielding state-of-the-art performance on the challenging ImageNet low-shot classification benchmark.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00760