Unsupervised Person Re-identification via Multi-Label Prediction and Classification based on Graph-Structural Insight

TL;DR

This paper introduces a novel unsupervised person re-identification method that leverages graph-structural insights for multi-label prediction and classification, achieving state-of-the-art results without pre-labeled data.

Contribution

It proposes a graph-structure based multi-label prediction and a selective multi-label classification loss for improved unsupervised person Re-ID.

Findings

Achieves state-of-the-art performance in unsupervised person Re-ID.

Effectively predicts multi-labels considering graph structure.

Boosts Re-ID accuracy without pre-labeled datasets.

Abstract

This paper addresses unsupervised person re-identification (Re-ID) using multi-label prediction and classification based on graph-structural insight. Our method extracts features from person images and produces a graph that consists of the features and a pairwise similarity of them as nodes and edges, respectively. Based on the graph, the proposed graph structure based multi-label prediction (GSMLP) method predicts multi-labels by considering the pairwise similarity and the adjacency node distribution of each node. The multi-labels created by GSMLP are applied to the proposed selective multi-label classification (SMLC) loss. SMLC integrates a hard-sample mining scheme and a multi-label classification. The proposed GSMLP and SMLC boost the performance of unsupervised person Re-ID without any pre-labelled dataset. Experimental results justify the superiority of the proposed method in unsupervised person Re-ID by producing state-of-the-art performance. The source code for this paper is publicly available on 'https://github.com/uknownpioneer/GSMLP-SMLC.git'.