Xu Zhang, Felix Xinnan Yu, Svebor Karaman, Wei Zhang, Shih-Fu Chang. Heated-Up Softmax Embedding. arXiv preprint arXiv:1809.04157, 2018.
Download paper:
Adobe portable document (pdf) 
Copyright notice:This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.
Metric learning aims at learning a distance which is consistent with the semantic meaning of the samples. The problem is generally solved by learning an embedding for each sample such that the embeddings of samples of the same category are compact while the embeddings of samples of different categories are spread-out in the feature space. We study the features extracted from the second last layer of a deep neural network based classifier trained with the cross entropy loss on top of the softmax layer. We show that training classifiers with different temperature values of softmax function leads to features with different levels of compactness. Leveraging these insights, we propose a "heating-up" strategy to train a classifier with increasing temperatures, leading the corresponding embeddings to achieve state-of-the-art performance on a variety of metric learning benchmarks
@article{zhang2018heated,
Author = {Zhang, Xu and Yu, Felix Xinnan and Karaman, Svebor and Zhang, Wei and Chang, Shih-Fu},
Title = {Heated-Up Softmax Embedding},
Journal = {arXiv preprint arXiv:1809.04157},
Year = {2018}
}
Get EndNote Reference (.ref)
For problems or questions regarding this web site contact The
Web Master.
This document was translated automatically from BibTEX by bib2html (Copyright 2003 © Eric Marchand, INRIA, Vista Project).
