Related papers: Shape Consistent 2D Keypoint Estimation under Doma…

Fully convolutional models for dense prediction have proven successful for a wide range of visual tasks. Such models perform well in a supervised setting, but performance can be surprisingly poor under domain shifts that appear mild to a…

While unsupervised domain adaptation has been explored to leverage the knowledge from a labeled source domain to an unlabeled target domain, existing methods focus on the distribution alignment between two domains. However, how to better…

Deep learning models for dermatological image analysis remain sensitive to acquisition variability and domain-specific visual characteristics, leading to performance degradation when deployed in clinical settings. We investigate how visual…

Unsupervised domain adaptation aims to transfer the classifier learned from the source domain to the target domain in an unsupervised manner. With the help of target pseudo-labels, aligning class-level distributions and learning the…

Cross-domain object detection is more challenging than object classification since multiple objects exist in an image and the location of each object is unknown in the unlabeled target domain. As a result, when we adapt features of…

Accurately describing and detecting 2D and 3D keypoints is crucial to establishing correspondences across images and point clouds. Despite a plethora of learning-based 2D or 3D local feature descriptors and detectors having been proposed,…

We propose in this paper a texture-invariant 2D keypoints descriptor specifically designed for matching preoperative Magnetic Resonance (MR) images with intraoperative Ultrasound (US) images. We introduce a matching-by-synthesis strategy,…

Deep neural networks are typically trained in a single shot for a specific task and data distribution, but in real world settings both the task and the domain of application can change. The problem becomes even more challenging in dense…

Domain shift, the mismatch between training and testing data characteristics, causes significant degradation in the predictive performance in multi-source imaging scenarios. In medical imaging, the heterogeneity of population, scanners and…

Most visual recognition methods implicitly assume the data distribution remains unchanged from training to testing. However, in practice domain shift often exists, where real-world factors such as lighting and sensor type change between…

The accuracy of deep learning (e.g., convolutional neural networks) for an image classification task critically relies on the amount of labeled training data. Aiming to solve an image classification task on a new domain that lacks labeled…

Domain adaptation is one of the most crucial techniques to mitigate the domain shift problem, which exists when transferring knowledge from an abundant labeled sourced domain to a target domain with few or no labels. Partial domain…

Unsupervised domain adaptation studies the problem of utilizing a relevant source domain with abundant labels to build predictive modeling for an unannotated target domain. Recent work observe that the popular adversarial approach of…

Supervised learning algorithms trained on medical images will often fail to generalize across changes in acquisition parameters. Recent work in domain adaptation addresses this challenge and successfully leverages labeled data in a source…

Many methods have been proposed to solve the domain adaptation problem recently. However, the success of them implicitly funds on the assumption that the information of domains are fully transferrable. If the assumption is not satisfied,…

Current state-of-the-art visual recognition systems usually rely on the following pipeline: (a) pretraining a neural network on a large-scale dataset (e.g., ImageNet) and (b) finetuning the network weights on a smaller, task-specific…

Unsupervised domain adaptation (UDA) has achieved unprecedented success in improving the cross-domain robustness of object detection models. However, existing UDA methods largely ignore the instantaneous data distribution during model…

3D object detectors are fundamental components of perception systems in autonomous vehicles. While these detectors achieve remarkable performance on standard autonomous driving benchmarks, they often struggle to generalize across different…

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…

Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias. Fine-tuning deep models in a new domain can require a significant amount of labeled data, which for…