Related papers: Multi-Domain Joint Training for Person Re-Identifi…
Information Retrieval (IR) practitioners often train separate ranking models for different domains (geographic regions, languages, stores, websites,...) as it is believed that exclusively training on in-domain data yields the best…
We aim to improve the performance of regressing hand keypoints and segmenting pixel-level hand masks under new imaging conditions (e.g., outdoors) when we only have labeled images taken under very different conditions (e.g., indoors). In…
Person re-identification (re-ID) aims at identifying the same persons' images across different cameras. However, domain diversities between different datasets pose an evident challenge for adapting the re-ID model trained on one dataset to…
Unsupervised cross-domain person re-identification (Re-ID) aims to adapt the information from the labelled source domain to an unlabelled target domain. Due to the lack of supervision in the target domain, it is crucial to identify the…
Deep neural networks can be unreliable in the real world when the training set does not adequately cover all the settings where they are deployed. Focusing on image classification, we consider the setting where we have an error distribution…
Unsupervised person re-identification (re-ID) remains a challenging task. While extensive research has focused on the framework design and loss function, this paper shows that sampling strategy plays an equally important role. We analyze…
Semantic segmentation models only perform well on the domain they are trained on and datasets for training are scarce and often have a small label-spaces, because the pixel level annotations required are expensive to make. Thus training…
Given a video or an image of a person acquired from a camera, person re-identification is the process of retrieving all instances of the same person from videos or images taken from a different camera with non-overlapping view. This task…
Domain adaptive person Re-Identification (ReID) is challenging owing to the domain gap and shortage of annotations on target scenarios. To handle those two challenges, this paper proposes a coupling optimization method including the…
This paper aims to learn a domain-generalizable (DG) person re-identification (ReID) representation from large-scale videos \textbf{without any annotation}. Prior DG ReID methods employ limited labeled data for training due to the high cost…
Robot learning holds the promise of learning policies that generalize broadly. However, such generalization requires sufficiently diverse datasets of the task of interest, which can be prohibitively expensive to collect. In other fields,…
Recently unsupervised person re-identification (re-ID) has drawn much attention due to its open-world scenario settings where limited annotated data is available. Existing supervised methods often fail to generalize well on unseen domains,…
Most existing studies on unsupervised domain adaptation (UDA) assume that each domain's training samples come with domain labels (e.g., painting, photo). Samples from each domain are assumed to follow the same distribution and the domain…
This paper mainly studies one-example and few-example video person re-identification. A multi-branch network PAM that jointly learns local and global features is proposed. PAM has high accuracy, few parameters and converges fast, which is…
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…
Unsupervised domain adaptation in person re-identification resorts to labeled source data to promote the model training on target domain, facing the dilemmas caused by large domain shift and large camera variations. The non-overlapping…
Data augmentation is one of the most effective techniques for regularizing deep learning models and improving their recognition performance in a variety of tasks and domains. However, this holds for standard in-domain settings, in which the…
Human intelligence can retrieve any person according to both visual and language descriptions. However, the current computer vision community studies specific person re-identification (ReID) tasks in different scenarios separately, which…
Most video person re-identification (re-ID) methods are mainly based on supervised learning, which requires cross-camera ID labeling. Since the cost of labeling increases dramatically as the number of cameras increases, it is difficult to…
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…