Learning View-Specific Deep Networks for Person Re-Identification

TL;DR

This paper introduces a view-specific deep learning framework for person re-identification that incorporates view information during feature extraction, significantly improving matching accuracy across different camera views.

Contribution

It proposes a novel view-specific network with cross-view constraints and an iterative optimization algorithm, advancing the state-of-the-art in person re-identification.

Findings

Outperforms existing deep networks on multiple benchmarks

Significantly improves re-id accuracy across camera views

Effectively reduces intra-class variations caused by viewpoint changes

Abstract

In recent years, a growing body of research has focused on the problem of person re-identification (re-id). The re-id techniques attempt to match the images of pedestrians from disjoint non-overlapping camera views. A major challenge of re-id is the serious intra-class variations caused by changing viewpoints. To overcome this challenge, we propose a deep neural network-based framework which utilizes the view information in the feature extraction stage. The proposed framework learns a view-specific network for each camera view with a cross-view Euclidean constraint (CV-EC) and a cross-view center loss (CV-CL). We utilize CV-EC to decrease the margin of the features between diverse views and extend the center loss metric to a view-specific version to better adapt the re-id problem. Moreover, we propose an iterative algorithm to optimize the parameters of the view-specific networks from coarse to fine. The experiments demonstrate that our approach significantly improves the performance of the existing deep networks and outperforms the state-of-the-art methods on the VIPeR, CUHK01, CUHK03, SYSU-mReId, and Market-1501 benchmarks.