Deep Unsupervised Image Hashing by Maximizing Bit Entropy

Authors

  • Yunqiang Li Delft University of Technology
  • Jan van Gemert Delft University of Technology

DOI:

https://doi.org/10.1609/aaai.v35i3.16296

Keywords:

Image and Video Retrieval

Abstract

Unsupervised hashing is important for indexing huge image or video collections without having expensive annotations available. Hashing aims to learn short binary codes for compact storage and efficient semantic retrieval. We propose an unsupervised deep hashing layer called Bi-Half Net that maximizes entropy of the binary codes. Entropy is maximal when both possible values of the bit are uniformly (half-half) distributed. To maximize bit entropy, we do not add a term to the loss function as this is difficult to optimize and tune. Instead, we design a new parameter-free network layer to explicitly force continuous image features to approximate the optimal half-half bit distribution. This layer is shown to minimize a penalized term of the Wasserstein distance between the learned continuous image features and the optimal half-half bit distribution. Experimental results on the image datasets FLICKR25K, NUS-WIDE, CIFAR-10, MS COCO, MNIST and the video datasets UCF-101 and HMDB-51 show that our approach leads to compact codes and compares favorably to the current state-of-the-art.

Downloads

Published

2021-05-18

How to Cite

Li, Y., & van Gemert, J. (2021). Deep Unsupervised Image Hashing by Maximizing Bit Entropy. Proceedings of the AAAI Conference on Artificial Intelligence, 35(3), 2002-2010. https://doi.org/10.1609/aaai.v35i3.16296

Issue

Section

AAAI Technical Track on Computer Vision II