Improved Person Re-Identification Based on Saliency and Semantic Parsing with Deep Neural Network Models

TL;DR

This paper introduces SSP-ReID, a framework that combines saliency and semantic parsing maps to enhance person re-identification accuracy using deep neural networks, achieving state-of-the-art results.

Contribution

The novel SSP-ReID framework effectively fuses saliency and semantic parsing clues to improve person re-identification across various network architectures and benchmarks.

Findings

Significant performance improvements over baseline models.

Achieved state-of-the-art results on three benchmarks.

Framework is compatible with multiple neural network backbones.

Abstract

Given a video or an image of a person acquired from a camera, person re-identification is the process of retrieving all instances of the same person from videos or images taken from a different camera with non-overlapping view. This task has applications in various fields, such as surveillance, forensics, robotics, multimedia. In this paper, we present a novel framework, named Saliency-Semantic Parsing Re-Identification (SSP-ReID), for taking advantage of the capabilities of both clues: saliency and semantic parsing maps, to guide a backbone convolutional neural network (CNN) to learn complementary representations that improves the results over the original backbones. The insight of fusing multiple clues is based on specific scenarios in which one response is better than another, thus favoring the combination of them to increase performance. Due to its definition, our framework can be easily applied to a wide variety of networks and, in contrast to other competitive methods, our training process follows simple and standard protocols. We present extensive evaluation of our approach through five backbones and three benchmarks. Experimental results demonstrate the effectiveness of our person re-identification framework. In addition, we combine our framework with re-ranking techniques to achieve state-of-the-art results on three benchmarks.