Visual Similarity from Optimizing Feature and Memory On A Hypersphere

Xinlei Pan, Rudrasis Chakraborty, Stella Yu; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 13-16

Abstract


Supervised learning of classification from annotated images develops a latent feature representation that captures semantic visual similarity. We propose an unsupervised metric learning method that develops apparent visual similarity from images alone. Our method maps high-dimensional visual data onto a low-dimensional hyper-sphere and consolidate such feature representations into a visual memory representation. Optimizing the feature mapping and visual memory on a hypersphere achieves maximal discrimination among instances. Our formulation and solution is not only more principled in theory than closely related unsupervised instance discrimination algorithms, but also better in practice in terms of classification accuracy, convergence rate, and feature transferability. We also show that our learned feature can be very useful for vision-based reinforcement learning tasks to improve sample efficiency.

Related Material


[pdf]
[bibtex]
@InProceedings{Pan_2019_CVPR_Workshops,
author = {Pan, Xinlei and Chakraborty, Rudrasis and Yu, Stella},
title = {Visual Similarity from Optimizing Feature and Memory On A Hypersphere},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}
}