FTN: Foreground-Guided Texture-Focused Person Re-Identification

TL;DR

This paper introduces FTN, a novel person re-identification network that emphasizes person-related attributes by focusing on foreground textures, reducing background interference, and achieving superior results on standard datasets.

Contribution

The paper proposes a foreground-guided, texture-focused network with a semi-supervised learning strategy and a new gradient loss for improved person re-ID performance.

Findings

Outperforms state-of-the-art methods on Market1501, CUHK03, and MSMT17 datasets.

Effectively weakens background influence and highlights person attributes.

Achieves computational efficiency in person re-identification tasks.

Abstract

Person re-identification (Re-ID) is a challenging task as persons are often in different backgrounds. Most recent Re-ID methods treat the foreground and background information equally for person discriminative learning, but can easily lead to potential false alarm problems when different persons are in similar backgrounds or the same person is in different backgrounds. In this paper, we propose a Foreground-Guided Texture-Focused Network (FTN) for Re-ID, which can weaken the representation of unrelated background and highlight the attributes person-related in an end-to-end manner. FTN consists of a semantic encoder (S-Enc) and a compact foreground attention module (CFA) for Re-ID task, and a texture-focused decoder (TF-Dec) for reconstruction task. Particularly, we build a foreground-guided semi-supervised learning strategy for TF-Dec because the reconstructed ground-truths are only the inputs of FTN weighted by the Gaussian mask and the attention mask generated by CFA. Moreover, a new gradient loss is introduced to encourage the network to mine the texture consistency between the inputs and the reconstructed outputs. Our FTN is computationally efficient and extensive experiments on three commonly used datasets Market1501, CUHK03 and MSMT17 demonstrate that the proposed method performs favorably against the state-of-the-art methods.