Related papers: Synthetic DOmain-Targeted Augmentation (S-DOTA) Im…

Data augmentation is widely known as a simple yet surprisingly effective technique for regularizing deep networks. Conventional data augmentation schemes, e.g., flipping, translation or rotation, are low-level, data-independent and…

Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset, making it applicable in a variety of real-world scenarios. Existing SFDA methods ONLY assess…

The main challenge in domain generalization (DG) is to handle the distribution shift problem that lies between the training and test data. Recent studies suggest that test-time training (TTT), which adapts the learned model with test data,…

Deep-learning models have been successful in biomedical image segmentation. To generalize for real-world deployment, test-time augmentation (TTA) methods are often used to transform the test image into different versions that are hopefully…

Open compound domain adaptation (OCDA) aims to transfer knowledge from a labeled source domain to a mix of unlabeled homogeneous compound target domains while generalizing to open unseen domains. Existing OCDA methods solve the intra-domain…

Domain Generalization (DG) is a challenging task in machine learning that requires a coherent ability to comprehend shifts across various domains through extraction of domain-invariant features. DG performance is typically evaluated by…

Domain shift is a major problem for deploying deep networks in clinical practice. Network performance drops significantly with (target) images obtained differently than its (source) training data. Due to a lack of target label data, most…

Data Augmentation (DA) is a technique to increase the quantity and diversity of the training data, and by that alleviate overfitting and improve generalisation. However, standard DA produces synthetic data for augmentation with limited…

Due to the COVID-19 global pandemic, computer-assisted diagnoses of medical images have gained much attention, and robust methods of semantic segmentation of Computed Tomography (CT) images have become highly desirable. In this work, we…

Frequent monitoring is necessary to stratify individuals based on their likelihood of developing gastrointestinal (GI) cancer precursors. In clinical practice, white-light imaging (WLI) and complementary modalities such as narrow-band…

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…

Synthetic data offers the promise of cheap and bountiful training data for settings where labeled real-world data is scarce. However, models trained on synthetic data significantly underperform when evaluated on real-world data. In this…

Generalization of neural networks is crucial for deploying them safely in the real world. Common training strategies to improve generalization involve the use of data augmentations, ensembling and model averaging. In this work, we first…

The application of supervised deep learning methods in digital pathology is limited due to their sensitivity to domain shift. Digital Pathology is an area prone to high variability due to many sources, including the common practice of…

Generalization is one of the key challenges in the clinical validation and application of deep learning models to medical images. Studies have shown that such models trained on publicly available datasets often do not work well on…

Detection transformers like DETR have recently shown promising performance on many object detection tasks, but the generalization ability of those methods is still quite challenging for cross-domain adaptation scenarios. To address the…

Stain variation is a phenomenon observed when distinct pathology laboratories stain tissue slides that exhibit similar but not identical color appearance. Due to this color shift between laboratories, convolutional neural networks (CNNs)…

The generalization with respect to domain shifts, as they frequently appear in applications such as autonomous driving, is one of the remaining big challenges for deep learning models. Therefore, we propose an exemplar-based style synthesis…

We introduce style augmentation, a new form of data augmentation based on random style transfer, for improving the robustness of convolutional neural networks (CNN) over both classification and regression based tasks. During training, our…

Domain generalization (DG) task aims to learn a robust model from source domains that could handle the out-of-distribution (OOD) issue. In order to improve the generalization ability of the model in unseen domains, increasing the diversity…