DeepHash: Getting Regularization, Depth and Fine-Tuning Right
This improves instance retrieval efficiency for applications like image search by enabling high compression without significant performance loss.
The paper tackled the problem of compressing high-dimensional image descriptors into compact binary hashes for instance retrieval, achieving up to 20% better performance than state-of-the-art methods and 512 times compression with 256-bit hashes.
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.