Deep Multi-Index Hashing for Person Re-Identification
This work addresses efficiency and accuracy challenges in person re-identification for large-scale surveillance applications, representing an incremental improvement over existing hashing methods.
The paper tackles the problem of inefficiency and accuracy loss in person re-identification (ReID) with large gallery sets by proposing deep multi-index hashing (DMIH), which integrates multi-index hashing and multi-branch networks, resulting in improved efficiency and accuracy over state-of-the-art baselines on three datasets.
Traditional person re-identification (ReID) methods typically represent person images as real-valued features, which makes ReID inefficient when the gallery set is extremely large. Recently, some hashing methods have been proposed to make ReID more efficient. However, these hashing methods will deteriorate the accuracy in general, and the efficiency of them is still not high enough. In this paper, we propose a novel hashing method, called deep multi-index hashing (DMIH), to improve both efficiency and accuracy for ReID. DMIH seamlessly integrates multi-index hashing and multi-branch based networks into the same framework. Furthermore, a novel block-wise multi-index hashing table construction approach and a search-aware multi-index (SAMI) loss are proposed in DMIH to improve the search efficiency. Experiments on three widely used datasets show that DMIH can outperform other state-of-the-art baselines, including both hashing methods and real-valued methods, in terms of both efficiency and accuracy.