Deep Region Hashing for Efficient Large-scale Instance Search from Images

TL;DR

This paper introduces Deep Region Hashing (DRH), an end-to-end neural network that efficiently performs large-scale instance search by generating region proposals, extracting features, and hashing them into compact binary codes for fast matching.

Contribution

The paper presents a novel end-to-end deep learning approach that integrates region proposal, feature extraction, and hashing, significantly improving efficiency and accuracy in large-scale instance search.

Findings

DRH achieves higher MAP than state-of-the-art methods.

DRH improves search efficiency by nearly 100 times.

End-to-end training enhances the effectiveness of instance search.

Abstract

Instance Search (INS) is a fundamental problem for many applications, while it is more challenging comparing to traditional image search since the relevancy is defined at the instance level. Existing works have demonstrated the success of many complex ensemble systems that are typically conducted by firstly generating object proposals, and then extracting handcrafted and/or CNN features of each proposal for matching. However, object bounding box proposals and feature extraction are often conducted in two separated steps, thus the effectiveness of these methods collapses. Also, due to the large amount of generated proposals, matching speed becomes the bottleneck that limits its application to large-scale datasets. To tackle these issues, in this paper we propose an effective and efficient Deep Region Hashing (DRH) approach for large-scale INS using an image patch as the query. Specifically, DRH is an end-to-end deep neural network which consists of object proposal, feature extraction, and hash code generation. DRH shares full-image convolutional feature map with the region proposal network, thus enabling nearly cost-free region proposals. Also, each high-dimensional, real-valued region features are mapped onto a low-dimensional, compact binary codes for the efficient object region level matching on large-scale dataset. Experimental results on four datasets show that our DRH can achieve even better performance than the state-of-the-arts in terms of MAP, while the efficiency is improved by nearly 100 times.