Quantcast

DeepHash: Getting Regularization, Depth and Fine-Tuning Right

Research paper by Jie Lin, Olivier Morere, Vijay Chandrasekhar, Antoine Veillard, Hanlin Goh

Indexed on: 19 Jan '15Published on: 19 Jan '15Published in: Computer Science - Computer Vision and Pattern Recognition



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 consistently outperforms state-of-the-art methods across all data sets for both Fisher Vectors and Deep Convolutional Neural Network features, by up to 20 percent over other schemes. The retrieval performance with 256-bit hashes is close to that of the uncompressed floating point features -- a remarkable 512 times compression.