Related papers: Domain Generalization with Adversarial Intensity A…

Domain generalization (DG), aiming at models able to work on multiple unseen domains, is a must-have characteristic of general artificial intelligence. DG based on single source domain training data is more challenging due to the lack of…

Recent works showed that Generative Adversarial Networks (GANs) can be successfully applied in unsupervised domain adaptation, where, given a labeled source dataset and an unlabeled target dataset, the goal is to train powerful classifiers…

Domain generalization (DG) for object detection aims to enhance detectors' performance in unseen scenarios. This task remains challenging due to complex variations in real-world applications. Recently, diffusion models have demonstrated…

It is imperative to ensure the robustness of deep learning models in critical applications such as, healthcare. While recent advances in deep learning have improved the performance of volumetric medical image segmentation models, these…

Generalizing to unseen image domains is a challenging problem primarily due to the lack of diverse training data, inaccessible target data, and the large domain shift that may exist in many real-world settings. As such data augmentation is…

Machine learning algorithms have revolutionized different fields, including natural language processing, computer vision, signal processing, and medical data processing. Despite the excellent capabilities of machine learning algorithms in…

The joint utilization of diverse data sources for medical imaging segmentation has emerged as a crucial area of research, aiming to address challenges such as data heterogeneity, domain shift, and data quality discrepancies. Integrating…

We present MaskGen, a theoretically grounded and deliberately simple approach for domain generalization in 3D biomedical image segmentation. Modern segmentation models degrade sharply under shifts in modality, disease severity, clinical…

Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems e.g., for classification, segmentation and object detection. The vulnerability of DNNs against such attacks can prove a major roadblock…

As designers of artificial intelligence try to outwit hackers, both sides continue to hone in on AI's inherent vulnerabilities. Designed and trained from certain statistical distributions of data, AI's deep neural networks (DNNs) remain…

The large number of trainable parameters of deep neural networks renders them inherently data hungry. This characteristic heavily challenges the medical imaging community and to make things even worse, many imaging modalities are ambiguous…

Collecting well-annotated image datasets to train modern machine learning algorithms is prohibitively expensive for many tasks. One appealing alternative is rendering synthetic data where ground-truth annotations are generated…

Single domain generalization (SDG) aims to train a robust model against unknown target domain shifts using data from a single source domain. Data augmentation has been proven an effective approach to SDG. However, the utility of standard…

Deep neural networks (DNN) have demonstrated unprecedented success for medical imaging applications. However, due to the issue of limited dataset availability and the strict legal and ethical requirements for patient privacy protection, the…

Given the widespread use of deep learning models in safety-critical applications, ensuring that the decisions of such models are robust against adversarial exploitation is of fundamental importance. In this thesis, we discuss recent…

Medical images are usually collected from multiple domains, leading to domain shifts that impair the performance of medical image segmentation models. Domain Generalization (DG) aims to address this issue by training a robust model with…

With the successful adoption of machine learning on electronic health records (EHRs), numerous computational models have been deployed to address a variety of clinical problems. However, due to the heterogeneity of EHRs, models trained on…

Recent progress in empirical and certified robustness promises to deliver reliable and deployable Deep Neural Networks (DNNs). Despite that success, most existing evaluations of DNN robustness have been done on images sampled from the same…

Deep learning techniques have achieved superior performance in computer-aided medical image analysis, yet they are still vulnerable to imperceptible adversarial attacks, resulting in potential misdiagnosis in clinical practice. Oppositely,…

Diabetic Retinopathy (DR) constitutes 5% of global blindness cases. While numerous deep learning approaches have sought to enhance traditional DR grading methods, they often falter when confronted with new out-of-distribution data thereby…