相关论文: Tightening Classification Boundaries in Open Set D…

Deep neural networks (DNNs) often perform poorly in the presence of domain shift and category shift. How to upcycle DNNs and adapt them to the target task remains an important open problem. Unsupervised Domain Adaptation (UDA), especially…

In semantic segmentation, we aim to train a pixel-level classifier to assign category labels to all pixels in an image, where labeled training images and unlabeled test images are from the same distribution and share the same label set.…

This paper presents a classification framework based on learnable data augmentation to tackle the One-Shot Unsupervised Domain Adaptation (OS-UDA) problem. OS-UDA is the most challenging setting in Domain Adaptation, as only one single…

Existing cross-network node classification methods are mainly proposed for closed-set setting, where the source network and the target network share exactly the same label space. Such a setting is restricted in real-world applications,…

Domain adaptation targets at knowledge acquisition and dissemination from a labeled source domain to an unlabeled target domain under distribution shift. Still, the common requirement of identical class space shared across domains hinders…

Detecting both known and unknown objects is a fundamental skill for robot manipulation in unstructured environments. Open-set object detection (OSOD) is a promising direction to handle the problem consisting of two subtasks: objects and…

Deep Neural Networks (DNNs) have recently been achieving state-of-the-art performance on a variety of computer vision related tasks. However, their computational cost limits their ability to be implemented in embedded systems with…

Universal domain adaptation (UniDA) has been proposed to transfer knowledge learned from a label-rich source domain to a label-scarce target domain without any constraints on the label sets. In practice, however, it is difficult to obtain a…

Unsupervised domain adaptation (UDA) for semantic segmentation has been attracting attention recently, as it could be beneficial for various label-scarce real-world scenarios (e.g., robot control, autonomous driving, medical imaging, etc.).…

Unsupervised domain adaptation uses source data from different distributions to solve the problem of classifying data from unlabeled target domains. However, conventional methods require access to source data, which often raise concerns…

Despite their success in various vision tasks, deep neural network architectures often underperform in out-of-distribution scenarios due to the difference between training and target domain style. To address this limitation, we introduce…

Building extraction $-$ needed for inventory management and planning of urban environment $-$ is affected by the misalignment between labels and off-nadir source imagery in training data. Teacher-Student learning of noise-tolerant…

Domain adaptation is a potential method to train a powerful deep neural network, which can handle the absence of labeled data. More precisely, domain adaptation solving the limitation called dataset bias or domain shift when the training…

Test-time adaptation (TTA) refers to adjusting the model during the testing phase to cope with changes in sample distribution and enhance the model's adaptability to new environments. In real-world scenarios, models often encounter samples…

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…

Current Domain Adaptation (DA) methods based on deep architectures assume that the source samples arise from a single distribution. However, in practice, most datasets can be regarded as mixtures of multiple domains. In these cases…

We address the problem of universal domain adaptation (UDA) in ordinal regression (OR), which attempts to solve classification problems in which labels are not independent, but follow a natural order. We show that the UDA techniques…

Existing techniques to adapt semantic segmentation networks across the source and target domains within deep convolutional neural networks (CNNs) deal with all the samples from the two domains in a global or category-aware manner. They do…

Test-Time Adaptation (TTA) aims to mitigate distributional shifts between training and test domains during inference time. However, existing TTA methods fall short in the realistic scenario where models face both continually changing…

Open Set Recognition (OSR) extends image classification to an open-world setting, by simultaneously classifying known classes and identifying unknown ones. While conventional OSR approaches can detect Out-of-Distribution (OOD) samples, they…