DeepHash: Getting Regularization, Depth and Fine-Tuning Right

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.

References in corpus (3)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• DeepPose: Human Pose Estimation via Deep Neural Networks
• Learning Hash Functions Using Column Generation

Cited by in corpus (8)

• Recent Advances in Convolutional Neural Networks
• Learning Deep Embeddings with Histogram Loss
• GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints
• Localizing and Orienting Street Views Using Overhead Imagery
• Siamese Capsule Networks
• Learning Spread-out Local Feature Descriptors
• Co-Regularized Deep Representations for Video Summarization
• Unsupervised Triplet Hashing for Fast Image Retrieval