Related papers: Mimic Embedding via Adaptive Aggregation: Learning…
In the current person Re-identification (ReID) methods, most domain generalization works focus on dealing with style differences between domains while largely ignoring unpredictable camera view change, which we identify as another major…
This work focuses on unsupervised representation learning in person re-identification (ReID). Recent self-supervised contrastive learning methods learn invariance by maximizing the representation similarity between two augmented views of a…
The application of federated domain generalization in person re-identification (FedDG-ReID) aims to enhance the model's generalization ability in unseen domains while protecting client data privacy. However, existing mainstream methods…
Despite the striking performance achieved by modern detectors when training and test data are sampled from the same or similar distribution, the generalization ability of detectors under unknown distribution shifts remains hardly studied.…
Person re-identification (Re-ID) is a critical technique in the video surveillance system, which has achieved significant success in the supervised setting. However, it is difficult to directly apply the supervised model to arbitrary unseen…
Domain generalizable person re-identification aims to apply a trained model to unseen domains. Prior works either combine the data in all the training domains to capture domain-invariant features, or adopt a mixture of experts to…
In recent years, supervised person re-identification (re-ID) models have received increasing studies. However, these models trained on the source domain always suffer dramatic performance drop when tested on an unseen domain. Existing…
Person re-identification (ReID) is aimed at identifying the same person across videos captured from different cameras. In the view that networks extracting global features using ordinary network architectures are difficult to extract local…
The problem of generalizing deep neural networks from multiple source domains to a target one is studied under two settings: When unlabeled target data is available, it is a multi-source unsupervised domain adaptation (UDA) problem,…
Unsupervised domain adaptation (UDA) aims at adapting the model trained on a labeled source-domain dataset to an unlabeled target-domain dataset. The task of UDA on open-set person re-identification (re-ID) is even more challenging as the…
Generalized Class Discovery (GCD) clusters base and novel classes in a target domain using supervision from a source domain with only base classes. Current methods often falter with distribution shifts and typically require access to target…
The Federated Domain Generalization for Person re-identification (FedDG-ReID) aims to learn a global server model that can be effectively generalized to source and target domains through distributed source domain data. Existing methods…
Person re-identification (ReID) is a fundamental task in many real-world applications such as pedestrian trajectory tracking. However, advanced deep learning-based ReID models are highly susceptible to adversarial attacks, where…
Face recognition systems are usually faced with unseen domains in real-world applications and show unsatisfactory performance due to their poor generalization. For example, a well-trained model on webface data cannot deal with the ID vs.…
Person re-identification (ReID) plays a critical role in intelligent surveillance systems by linking identities across multiple cameras in complex environments. However, ReID faces significant challenges such as appearance variations,…
Person re-identification (re-id) is the task of matching multiple occurrences of the same person from different cameras, poses, lighting conditions, and a multitude of other factors which alter the visual appearance. Typically, this is…
Unsupervised domain adaptation techniques have been successful for a wide range of problems where supervised labels are limited. The task is to classify an unlabeled `target' dataset by leveraging a labeled `source' dataset that comes from…
In this technical report, we present our submission to the VisDA Challenge in ECCV 2020 and we achieved one of the top-performing results on the leaderboard. Our solution is based on Structured Domain Adaptation (SDA) and Mutual…
Person re-identification (ReID) under occlusions is a challenging problem in video surveillance. Most of existing person ReID methods take advantage of local features to deal with occlusions. However, these methods usually independently…
Domain generalization(DG) endeavors to develop robust models that possess strong generalizability while preserving excellent discriminability. Nonetheless, pivotal DG techniques tend to improve the feature generalizability by learning…