Related papers: A benchmark with decomposed distribution shifts fo…

Deep learning (DL) techniques have achieved great success in predictive accuracy in a variety of tasks, but deep neural networks (DNNs) are shown to produce highly overconfident scores for even abnormal samples. Well-defined uncertainty…

A novel variational inference based resampling framework is proposed to evaluate the robustness and generalization capability of deep learning models with respect to distribution shift. We use Auto Encoding Variational Bayes to find a…

We propose a semi-supervised learning framework for monocular depth estimation. Compared to existing semi-supervised learning methods, which inherit limitations of both sparse supervised and unsupervised loss functions, we achieve the…

Covariate shifts are a common problem in predictive modeling on real-world problems. This paper proposes addressing the covariate shift problem by minimizing Maximum Mean Discrepancy (MMD) statistics between the training and test sets in…

Obtaining accurate depth measurements out of a single image represents a fascinating solution to 3D sensing. CNNs led to considerable improvements in this field, and recent trends replaced the need for ground-truth labels with…

We propose SharpDepth, a novel approach to monocular metric depth estimation that combines the metric accuracy of discriminative depth estimation methods (e.g., Metric3D, UniDepth) with the fine-grained boundary sharpness typically achieved…

Estimating depth from a single RGB images is a fundamental task in computer vision, which is most directly solved using supervised deep learning. In the field of unsupervised learning of depth from a single RGB image, depth is not given…

Trusting the predictions of deep learning models in safety critical settings such as the medical domain is still not a viable option. Distentangled uncertainty quantification in the field of medical imaging has received little attention. In…

Single-view depth estimation refers to the ability to derive three-dimensional information per pixel from a single two-dimensional image. Single-view depth estimation is an ill-posed problem because there are multiple depth solutions that…

Distribution shifts -- where the training distribution differs from the test distribution -- can substantially degrade the accuracy of machine learning (ML) systems deployed in the wild. Despite their ubiquity in the real-world deployments,…

Out-of-distribution (OOD) learning deals with scenarios in which training and test data follow different distributions. Although general OOD problems have been intensively studied in machine learning, graph OOD is only an emerging area of…

Image segmentation is the foundation of several computer vision tasks, where pixel-wise knowledge is a prerequisite for achieving the desired target. Deep learning has shown promising performance in supervised image segmentation. However,…

Deep learning models have gained increasing adoption in medical image analysis. However, these models often produce overconfident predictions, which can compromise clinical accuracy and reliability. Bridging the gap between high-performance…

Deep learning has recently achieved initial success in program analysis tasks such as bug detection. Lacking real bugs, most existing works construct training and test data by injecting synthetic bugs into correct programs. Despite…

Reliable generalization metrics are fundamental to the evaluation of machine learning models. Especially in high-stakes applications where labeled target data are scarce, evaluation of models' generalization performance under distribution…

Monocular visual odometry consists of the estimation of the position of an agent through images of a single camera, and it is applied in autonomous vehicles, medical robots, and augmented reality. However, monocular systems suffer from the…

Many researchers have identified distribution shift as a likely contributor to the reproducibility crisis in behavioral and biomedical sciences. The idea is that if treatment effects vary across individual characteristics and experimental…

Understanding the performance of machine learning models across diverse data distributions is critically important for reliable applications. Motivated by this, there is a growing focus on curating benchmark datasets that capture…

Deep learning has shown tremendous progress in a wide range of digital pathology and medical image classification tasks. Its integration into safe clinical decision-making support requires robust and reliable models. However, real-world…

Depth estimation from a single image is a challenging problem in computer vision because binocular disparity or motion information is absent. Whereas impressive performances have been reported in this area recently using end-to-end trained…