相关论文: Exploring Robustness of Unsupervised Domain Adapta…

Unsupervised Domain Adaptation (UDA) aims to leverage a label-rich source domain to solve tasks on a related unlabeled target domain. It is a challenging problem especially when a large domain gap lies between the source and target domains.…

Adversarial examples are inevitable on the road of pervasive applications of deep neural networks (DNN). Imperceptible perturbations applied on natural samples can lead DNN-based classifiers to output wrong prediction with fair confidence…

Adversarial attacks have been fairly explored for computer vision and vision-language models. However, the avenue of adversarial attack for the vision language segmentation models (VLSMs) is still under-explored, especially for medical…

In this paper, we tackle the unsupervised domain adaptation (UDA) for semantic segmentation, which aims to segment the unlabeled real data using labeled synthetic data. The main problem of UDA for semantic segmentation relies on reducing…

While deep learning methods hitherto have achieved considerable success in medical image segmentation, they are still hampered by two limitations: (i) reliance on large-scale well-labeled datasets, which are difficult to curate due to the…

Although unsupervised domain adaptation methods have achieved remarkable performance in semantic scene segmentation in visual perception for self-driving cars, these approaches remain impractical in real-world use cases. In practice, the…

Recent unsupervised domain adaptation (UDA) methods have shown great success in addressing classical domain shifts (e.g., synthetic-to-real), but they still suffer under complex shifts (e.g. geographical shift), where both the background…

Learning semantic segmentation models requires a huge amount of pixel-wise labeling. However, labeled data may only be available abundantly in a domain different from the desired target domain, which only has minimal or no annotations. In…

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…

Neural networks are prone to misclassify slightly modified input images. Recently, many defences have been proposed, but none have improved the robustness of neural networks consistently. Here, we propose to use adversarial attacks as a…

Unsupervised domain adaptation (UDA) for semantic segmentation aims to transfer the pixel-wise knowledge from the labeled source domain to the unlabeled target domain. However, current UDA methods typically assume a shared label space…

Unsupervised Domain Adaptation for Remote Sensing Semantic Segmentation (UDA-RSSeg) addresses the challenge of adapting a model trained on source domain data to target domain samples, thereby minimizing the need for annotated data across…

Deep learning models can be fooled by small $l_p$-norm adversarial perturbations and natural perturbations in terms of attributes. Although the robustness against each perturbation has been explored, it remains a challenge to address the…

Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains. They also can improve recognition despite the presence of domain shift or dataset bias: several…

Traditional machine learning assumes that training and test sets are derived from the same distribution; however, this assumption does not always hold in practical applications. This distribution disparity can lead to severe performance…

Vision transformer has demonstrated great potential in abundant vision tasks. However, it also inevitably suffers from poor generalization capability when the distribution shift occurs in testing (i.e., out-of-distribution data). To…

Unsupervised Domain Adaptation (UDA) can tackle the challenge that convolutional neural network(CNN)-based approaches for semantic segmentation heavily rely on the pixel-level annotated data, which is labor-intensive. However, existing UDA…

Deep neural networks are at the forefront of machine learning research. However, despite achieving impressive performance on complex tasks, they can be very sensitive: Small perturbations of inputs can be sufficient to induce incorrect…

The rise of computer vision applications in the real world puts the security of the deep neural networks at risk. Recent works demonstrate that convolutional neural networks are susceptible to adversarial examples - where the input images…

Unsupervised domain adaptation (UDA) and domain generalization (DG) enable machine learning models trained on a source domain to perform well on unlabeled or even unseen target domains. As previous UDA&DG semantic segmentation methods are…