Related papers: Aligned Divergent Pathways for Omni-Domain General…
Unsupervised domain adaptation for person re-identification (Person Re-ID) is the task of transferring the learned knowledge on the labeled source domain to the unlabeled target domain. Most of the recent papers that address this problem…
Point-cloud-based 3D object detection suffers from performance degradation when encountering data with novel domain gaps. To tackle it, the single-domain generalization (SDG) aims to generalize the detection model trained in a limited…
Adversarial discriminative domain adaptation (ADDA) is an efficient framework for unsupervised domain adaptation in image classification, where the source and target domains are assumed to have the same classes, but no labels are available…
In this work, we address the problem of unsupervised domain adaptation for person re-ID where annotations are available for the source domain but not for target. Previous methods typically follow a two-stage optimization pipeline, where the…
In real-world applications, deep learning models often run in non-stationary environments where the target data distribution continually shifts over time. There have been numerous domain adaptation (DA) methods in both online and offline…
Existing unsupervised person re-identification (ReID) methods focus on adapting a model trained on a source domain to a fixed target domain. However, an adapted ReID model usually only works well on a certain target domain, but can hardly…
In this work, we focus on text-based person retrieval, which identifies individuals based on textual descriptions. Despite advancements enabled by synthetic data for pretraining, a significant domain gap, due to variations in lighting,…
Aerial-Ground Person Re-IDentification (AG-ReID) aims to retrieve specific persons across cameras with different viewpoints. Previous works focus on designing discriminative models to maintain the identity consistency despite drastic…
Moment-based distributionally robust optimization (DRO) provides an optimization framework to integrate statistical information with traditional optimization approaches. Under this framework, one assumes that the underlying joint…
Training a deep architecture using a ranking loss has become standard for the person re-identification task. Increasingly, these deep architectures include additional components that leverage part detections, attribute predictions, pose…
Person Re-Identification (Re-ID) task seeks to enhance the tracking of multiple individuals by surveillance cameras. It supports multimodal tasks, including text-based person retrieval and human matching. One of the most significant…
Cross-domain transfer learning (CDTL) is an extremely challenging task for the person re-identification (ReID). Given a source domain with annotations and a target domain without annotations, CDTL seeks an effective method to transfer the…
Stochastic optimization plays a crucial role in the advancement of deep learning technologies. Over the decades, significant effort has been dedicated to improving the training efficiency and robustness of deep neural networks, via various…
Due to domain shift, deep neural networks (DNNs) usually fail to generalize well on unknown test data in practice. Domain generalization (DG) aims to overcome this issue by capturing domain-invariant representations from source domains.…
Existing fully-supervised person re-identification (ReID) methods usually suffer from poor generalization capability caused by domain gaps. The key to solving this problem lies in filtering out identity-irrelevant interference and learning…
Learning generic and robust feature representations with data from multiple domains for the same problem is of great value, especially for the problems that have multiple datasets but none of them are large enough to provide abundant data…
A big challenge of person re-identification (Re-ID) using a multi-branch network architecture is to learn diverse features from the ID-labeled dataset. The 2-branch Batch DropBlock (BDB) network was recently proposed for achieving diversity…
Machine learning models fail to perform when facing out-of-distribution (OOD) domains, a challenging task known as domain generalization (DG). In this work, we develop a novel DG training strategy, we call PGrad, to learn a robust gradient…
Domain adaptive person re-identification (re-ID) is a challenging task, especially when person identities in target domains are unknown. Existing methods attempt to address this challenge by transferring image styles or aligning feature…
Existing person re-identification (re-ID) research mainly focuses on pedestrian identity matching across cameras in adjacent areas. However, in reality, it is inevitable to face the problem of pedestrian identity matching across…