Related papers: Learning from Temporal Spatial Cubism for Cross-Da…
Unsupervised Domain Adaptation (UDA) for semantic segmentation has been favorably applied to real-world scenarios in which pixel-level labels are hard to be obtained. In most of the existing UDA methods, all target data are assumed to be…
In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and…
In recent years, self-supervised representation learning for skeleton-based action recognition has advanced with the development of contrastive learning methods. However, most of contrastive paradigms are inherently discriminative and often…
Object detectors trained on large-scale RGB datasets are being extensively employed in real-world applications. However, these RGB-trained models suffer a performance drop under adverse illumination and lighting conditions. Infrared (IR)…
Unsupervised Domain Adaptation (UDA) has emerged as a powerful solution for the domain shift problem via transferring the knowledge from a labeled source domain to a shifted unlabeled target domain. Despite the prevalence of UDA for visual…
Unsupervised domain adaptation (UDA) involves adapting a model trained on a label-rich source domain to an unlabeled target domain. However, in real-world scenarios, the absence of target-domain labels makes it challenging to evaluate the…
In skeleton-based action recognition, Graph Convolutional Networks model human skeletal joints as vertices and connect them through an adjacency matrix, which can be seen as a local attention mask. However, in most existing Graph…
Person Re-Identification (re-ID) aims at retrieving images of the same person taken by different cameras. A challenge for re-ID is the performance preservation when a model is used on data of interest (target data) which belong to a…
Concept Bottleneck Models (CBMs) enhance interpretability by explaining predictions through human-understandable concepts but typically assume that training and test data share the same distribution. This assumption often fails under domain…
Instance contrast for unsupervised representation learning has achieved great success in recent years. In this work, we explore the idea of instance contrastive learning in unsupervised domain adaptation (UDA) and propose a novel Category…
The dynamics of human skeletons have significant information for the task of action recognition. The similarity between trajectories of corresponding joints is an indicating feature of the same action, while this similarity may subject to…
Simulation data can be accurately labeled and have been expected to improve the performance of data-driven algorithms, including object detection. However, due to the various domain inconsistencies from simulation to reality…
Existing deep learning-based change detection methods try to elaborately design complicated neural networks with powerful feature representations, but ignore the universal domain shift induced by time-varying land cover changes, including…
Deep learning has demonstrated remarkable performance across various tasks in medical imaging. However, these approaches primarily focus on supervised learning, assuming that the training and testing data are drawn from the same…
Unsupervised domain adaptation methods aim to generalize well on unlabeled test data that may have a different (shifted) distribution from the training data. Such methods are typically developed on image data, and their application to time…
Supervised learning with large scale labeled datasets and deep layered models has made a paradigm shift in diverse areas in learning and recognition. However, this approach still suffers generalization issues under the presence of a domain…
Self-supervised pretraining methods with masked prediction demonstrate remarkable within-dataset performance in skeleton-based action recognition. However, we show that, unlike contrastive learning approaches, they do not produce…
Unsupervised domain adaptation (UDA) aims to transfer the knowledge on a labeled source domain distribution to perform well on an unlabeled target domain. Recently, the deep self-training involves an iterative process of predicting on the…
Semi-supervised action recognition aims to improve spatio-temporal reasoning ability with a few labeled data in conjunction with a large amount of unlabeled data. Albeit recent advancements, existing powerful methods are still prone to…
In this work, we tackle the problem of unsupervised domain adaptation (UDA) for video action recognition. Our approach, which we call UNITE, uses an image teacher model to adapt a video student model to the target domain. UNITE first…