A review of Recent Techniques for Person Re-Identification

Abstract

Person re-identification (ReId), a crucial task in surveillance, involves matching individuals across different camera views. The advent of Deep Learning, especially supervised techniques like Convolutional Neural Networks and Attention Mechanisms, has significantly enhanced person Re-ID. However, the success of supervised approaches hinges on vast amounts of annotated data, posing scalability challenges in data labeling and computational costs. To address these limitations, recent research has shifted towards unsupervised person re-identification. Leveraging abundant unlabeled data, unsupervised methods aim to overcome the need for pairwise labelled data. Although traditionally trailing behind supervised approaches, unsupervised techniques have shown promising developments in recent years, signalling a narrowing performance gap. Motivated by this evolving landscape, our survey pursues two primary objectives. First, we review and categorize significant publications in supervised person re-identification, providing an in-depth overview of the current state-of-the-art and emphasizing little room for further improvement in this domain. Second, we explore the latest advancements in unsupervised person re-identification over the past three years, offering insights into emerging trends and shedding light on the potential convergence of performance between supervised and unsupervised paradigms. This dual-focus survey aims to contribute to the evolving narrative of person re-identification, capturing both the mature landscape of supervised techniques and the promising outcomes in the realm of unsupervised learning.

References in corpus (15)

• Deep Visual Domain Adaptation: A Survey
• Learning Discriminative Features with Multiple Granularities for Person Re-Identification
• DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
• Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)
• Cluster-guided Asymmetric Contrastive Learning for Unsupervised Person Re-Identification
• Learning to Purification for Unsupervised Person Re-identification
• Hybrid Dynamic Contrast and Probability Distillation for Unsupervised Person Re-Id
• Significance of Softmax-based Features in Comparison to Distance Metric Learning-based Features
• Learning to Disentangle Scenes for Person Re-identification
• Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification
• Improved Person Re-Identification Based on Saliency and Semantic Parsing with Deep Neural Network Models
• Unsupervised Person Re-identification with Stochastic Training Strategy
• CA-Jaccard: Camera-aware Jaccard Distance for Person Re-identification
• Deep Learning Technique for Human Parsing: A Survey and Outlook
• Unsupervised Person Re-Identification: A Systematic Survey of Challenges and Solutions