Fig 4 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Feature alignment for domain adaptation. Mid-level attribute features are align between source and target domain in a joint learning pipeline.
Source publication
Person re-identification (Re-ID) has been a significant research topic in the past decade due to its real-world applications and research significance. While supervised person Re-ID methods achieve superior performance over unsupervised counterparts, they can not scale to large unlabelled datasets and new domains due to the prohibitive labelling co...
Citations
... To tackle the domain adaptation issue associated with supervised person Re-ID, recent research has focused on unsupervised person re-identification, which involves training Re-ID models using abundant unlabeled data. The performance of unsupervised person Re-ID tends to be generally inferior to that of supervised person Re-ID, due to the challenges posed by the absence of pairwise labelled data for training camera-invariant representations of individual features [16]. However, in recent years, this performance gap has been diminishing, showing promising results [17,18]. ...
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.
