Related papers: DOMINO: Domain-aware Loss for Deep Learning Calibr…

Deep learning models, including modern systems like large language models, are well known to offer unreliable estimates of the uncertainty of their decisions. In order to improve the quality of the confidence levels, also known as…

Calibration error is commonly adopted for evaluating the quality of uncertainty estimators in deep neural networks. In this paper, we argue that such a metric is highly beneficial for training predictive models, even when we do not…

Generalization capability to unseen domains is crucial for machine learning models when deploying to real-world conditions. We investigate the challenging problem of domain generalization, i.e., training a model on multi-domain source data…

In critical decision support systems based on medical imaging, the reliability of AI-assisted decision-making is as relevant as predictive accuracy. Although deep learning models have demonstrated significant accuracy, they frequently…

Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. This problem usually arises due to the overfitting problem, which is characterized by learning everything presented in the…

The deep learning technique has been shown to be effectively addressed several image analysis tasks in the computer-aided diagnosis scheme for mammography. The training of an efficacious deep learning model requires large data with diverse…

Simultaneous segmentation of multiple organs from different medical imaging modalities is a crucial task as it can be utilized for computer-aided diagnosis, computer-assisted surgery, and therapy planning. Thanks to the recent advances in…

Proper confidence calibration of deep neural networks is essential for reliable predictions in safety-critical tasks. Miscalibration can lead to model over-confidence and/or under-confidence; i.e., the model's confidence in its prediction…

Deep-learning has proved in recent years to be a powerful tool for image analysis and is now widely used to segment both 2D and 3D medical images. Deep-learning segmentation frameworks rely not only on the choice of network architecture but…

Deep learning based object detectors struggle generalizing to a new target domain bearing significant variations in object and background. Most current methods align domains by using image or instance-level adversarial feature alignment.…

Uncertainty is a fundamental aspect of real-world scenarios, where perfect information is rarely available. Humans naturally develop complex internal models to navigate incomplete data and effectively respond to unforeseen or partially…

Deep neural networks (DNNs) have enabled astounding progress in several vision-based problems. Despite showing high predictive accuracy, recently, several works have revealed that they tend to provide overconfident predictions and thus are…

In medical imaging, the heterogeneity of multi-centre data impedes the applicability of deep learning-based methods and results in significant performance degradation when applying models in an unseen data domain, e.g. a new centreor a new…

Image alignment across domains has recently become one of the realistic and popular topics in the research community. In this problem, a deep learning-based image alignment method is usually trained on an available largescale database.…

Knowledge of the domain of applicability of a machine learning model is essential to ensuring accurate and reliable model predictions. In this work, we develop a new and general approach of assessing model domain and demonstrate that our…

Fine-tuning is arguably the most straightforward way to tailor a pre-trained model (e.g., a foundation model) to downstream applications, but it also comes with the risk of losing valuable knowledge the model had learned in pre-training.…

Estimates of predictive uncertainty are important for accurate model-based planning and reinforcement learning. However, predictive uncertainties---especially ones derived from modern deep learning systems---can be inaccurate and impose a…

Traditional place categorization approaches in robot vision assume that training and test images have similar visual appearance. Therefore, any seasonal, illumination and environmental changes typically lead to severe degradation in…

Nowadays, users open multiple accounts on social media platforms and e-commerce sites, expressing their personal preferences on different domains. However, users' behaviors change across domains, depending on the content that users interact…

Deep learning has played a major role in the interpretation of dermoscopic images for detecting skin defects and abnormalities. However, current deep learning solutions for dermatological lesion analysis are typically limited in providing…