Related papers: SweiNet: Deep Learning Based Uncertainty Quantific…

Uncertainty quantification is an important and challenging problem in deep learning. Previous methods rely on dropout layers which are not present in modern deep architectures or batch normalization which is sensitive to batch sizes. In…

Accurate and reliable tumor segmentation is essential in medical imaging analysis for improving diagnosis, treatment planning, and monitoring. However, existing segmentation models often lack robust mechanisms for quantifying the…

Deep learning methods for unsupervised registration often rely on objectives that assume a uniform noise level across the spatial domain (e.g. mean-squared error loss), but noise distributions are often heteroscedastic and input-dependent…

Uncertainty quantification is a critical yet unsolved challenge for deep learning, especially for the time series imputation with irregularly sampled measurements. To tackle this problem, we propose a novel framework based on the principles…

Weakly-Supervised Semantic Segmentation (WSSS) segments objects without a heavy burden of dense annotation. While as a price, generated pseudo-masks exist obvious noisy pixels, which result in sub-optimal segmentation models trained over…

Deploying deep learning (DL) models in medical applications relies on predictive performance and other critical factors, such as conveying trustworthy predictive uncertainty. Uncertainty estimation (UE) methods provide potential solutions…

The estimation of 6D object poses is a fundamental task in many computer vision applications. Particularly, in high risk scenarios such as human-robot interaction, industrial inspection, and automation, reliable pose estimates are crucial.…

To develop and validate a fully automated, deep-learning pipeline for measuring glenoid bone loss on 3D CT scans using linear-based, en-face view, and best-circle method. Shoulder CT scans of 81 patients were retrospectively collected…

Designing a deep neural network (DNN) with good generalization capability is a complex process especially when the weights are severely quantized. Model averaging is a promising approach for achieving the good generalization capability of…

Surface normal estimation from a single image is an important task in 3D scene understanding. In this paper, we address two limitations shared by the existing methods: the inability to estimate the aleatoric uncertainty and lack of detail…

To model time series accurately is important within a wide range of fields. As the world is generally too complex to be modelled exactly, it is often meaningful to assess the probability of a dynamical system to be in a specific state. This…

Speech, Music and Noise classification/segmentation is an important preprocessing step for audio processing/indexing. To this end, we propose a novel 1D Convolutional Neural Network (CNN) - SwishNet. It is a fast and lightweight…

Bayesian neural networks and deep ensemble methods have been proposed for uncertainty quantification; however, they are computationally intensive and require large storage. By utilizing a single deterministic model, we can solve the above…

Accurate segmentation of brain tumors is vital for diagnosis, surgical planning, and treatment monitoring. Deep learning has advanced on benchmarks, but two issues limit clinical use: no uncertainty estimates for errors and no segmentation…

Uncertainty in biological neural systems appears to be computationally beneficial rather than detrimental. However, in neuromorphic computing systems, device variability often limits performance, including accuracy and efficiency. In this…

In this paper, we describe a Bayesian deep neural network (DNN) for predicting FreeSurfer segmentations of structural MRI volumes, in minutes rather than hours. The network was trained and evaluated on a large dataset (n = 11,480), obtained…

Fast estimates of model uncertainty are required for many robust robotics applications. Deep Ensembles provides state of the art uncertainty without requiring Bayesian methods, but still it is computationally expensive. In this paper we…

We investigate the convergence rates and data sample sizes required for training a machine learning model using a stochastic gradient descent (SGD) algorithm, where data points are sampled based on either their loss value or uncertainty…

Slimmable Neural Networks (S-Net) is a novel network which enabled to select one of the predefined proportions of channels (sub-network) dynamically depending on the current computational resource availability. The accuracy of each…

Self-supervised depth estimation has drawn much attention in recent years as it does not require labeled data but image sequences. Moreover, it can be conveniently used in various applications, such as autonomous driving, robotics,…