DeepHash for Image Instance Retrieval: Getting Regularization, Depth and Fine-Tuning Right

DeepHash for Image Instance Retrieval: Getting Regularization, Depth and Fine-Tuning Right
Title:
DeepHash for Image Instance Retrieval: Getting Regularization, Depth and Fine-Tuning Right
Other Titles:
Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval (ICMR)
Publication Date:
06 June 2017
Citation:
Abstract:
This work focuses on representing very high-dimensional global image descriptors using very compact 64-1024 bit binary hashes for instance retrieval. We propose DeepHash: a hashing scheme based on deep networks. Key to making DeepHash work at extremely low bitrates are three important considerations -- regularization, depth and fine-tuning -- each requiring solutions specific to the hashing problem. In-depth evaluation shows that our scheme outperforms state-of-the-art methods over several benchmark datasets for both Fisher Vectors and Deep Convolutional Neural Network features, by up to 8.5% over other schemes. The retrieval performance with 256-bit hashes is close to that of the uncompressed floating point features -- a remarkable 512x compression.
License type:
PublisherCopyrights
Funding Info:
Description:
© ACM 2017. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in http://dx.doi.org/10.1145/3078971.3078983
ISBN:
978-1-4503-4701-3
Files uploaded:

File Size Format Action
sample-deephash.pdf 744.41 KB PDF Open