Introduction

Existing person re-identification (re-id) methods typically assume that (1) any probe person is guaranteed to appear in the gallery target population during deployment (i.e. closed-world), and (2) the probe set contains only a limited number of people (i.e. small search scale). Both assumptions are artificial and breached in real-world applications, since the probe population in target people search can be extremely vast in practice due to the ambiguity of probe search space boundary. Therefore, it is unrealistic that any probe person is assumed as one target people, and a large-scale search in person images is inherently demanded. In this work, we introduce a new person re-id search setting, called Large Scale Open-World (LSOW) reid, characterised by huge size probe images and open person population in search thus more close to practical deployments. Under LSOW, the under-studied problem of person re-id efficiency is essential in addition to that of commonly-studied re-id accuracy. We therefore develop a novel fast person re-id method, called Cross-view Identity Correlation and vErification (X-ICE) hashing, for joint learning of cross-view identity representation binarisation and discrimination in a unified manner. Extensive comparative experiments on three large scale benchmarks have been conducted to validate the superiority and advantages of the proposed X-ICE method over a wide range of the state-of-the-art hashing models, person re-id methods, and their combinations.

Contribution Highlights

  • We propose a more realistic Large Scale Open-World (LSOW) person reid problem. The LSOW eliminates two artificial assumptions made by existing re-id models that fundamentally prevent them from being scalable and applicable to real-world deployments
  • We develop a new person re-id method, called Cross-view Identity Correlation and vErification (X-ICE), for efficiently and effectively addressing LSOW re-id matching. In particular, X-ICE learns a re-id discriminative binary coding space by simultaneous cross-view identity correlation hashing and person class discrimination verification.
  • We extensively evaluate a wide range (14) of state-of-the-art hashing methods for LSOW person re-id. To our knowledge, this is the first attempt to investigate fast search solutions for large scale re-id in open world.

Citation

  1. Fast Open-World Person Re-Identification
    X. Zhu, B. Wu, D. Huang and W-S Zheng.
    IEEE Transactions on Image Processing, Vol. 27, No. 5, pp. 2286-2300, May 2018 (TIP)

Download codes and datasets

Codes [293 KB] Datasets [272 MB]