Related papers: Two-Dimensional Unknown View Tomography from Unkno…
There are many approaches to weakly-supervised training of networks to segment 2D images. By contrast, existing approaches to segmenting volumetric images rely on full-supervision of a subset of 2D slices of the 3D volume. We propose an…
We introduce a new rotationally invariant viewing angle classification method for identifying, among a large number of Cryo-EM projection images, similar views without prior knowledge of the molecule. Our rotationally invariant features are…
We propose a distributed positioning algorithm to estimate the unknown positions of a number of target nodes, given distance measurements between target nodes and between target nodes and a number of reference nodes at known positions.…
Object placement is a fundamental task for robots, yet it remains challenging for partially observed objects. Existing methods for object placement have limitations, such as the requirement for a complete 3D model of the object or the…
Despite their successes, deep neural networks may make unreliable predictions when faced with test data drawn from a distribution different to that of the training data, constituting a major problem for AI safety. While this has recently…
Robustness to out-of-distribution (OOD) data is an important goal in building reliable machine learning systems. Especially in autonomous systems, wrong predictions for OOD inputs can cause safety critical situations. As a first step…
Unsupervised landmarks discovery (ULD) for an object category is a challenging computer vision problem. In pursuit of developing a robust ULD framework, we explore the potential of a recent paradigm of self-supervised learning algorithms,…
Deep neural networks (DNNs) are often constructed under the closed-world assumption, which may fail to generalize to the out-of-distribution (OOD) data. This leads to DNNs producing overconfident wrong predictions and can result in…
Contrast-enhanced Computed Tomography (CT) is important for diagnosis and treatment planning for various medical conditions. Deep learning (DL) based segmentation models may enable automated medical image analysis for detecting and…
This work presents a probabilistic deep neural network that combines LiDAR point clouds and RGB camera images for robust, accurate 3D object detection. We explicitly model uncertainties in the classification and regression tasks, and…
Many real-world vision problems suffer from inherent ambiguities. In clinical applications for example, it might not be clear from a CT scan alone which particular region is cancer tissue. Therefore a group of graders typically produces a…
The importance of ultrasonic nondestructive testing has been increasing in recent years, and there are high expectations for the potential of laser ultrasonic visualization testing, which combines laser ultrasonic testing with scattered…
Uncertainty estimation aims to evaluate the confidence of a trained deep neural network. However, existing uncertainty estimation approaches rely on low-dimensional distributional assumptions and thus suffer from the high dimensionality of…
Congenital uterine anomalies (CUAs) can lead to infertility, miscarriage, preterm birth, and an increased risk of pregnancy complications. Compared to traditional 2D ultrasound (US), 3D US can reconstruct the coronal plane, providing a…
Ultrasound modulated bioluminescence tomography (UMBLT) is an imaging method which can be formulated as a hybrid inverse source problem. In the regime where light propagation is modeled by a radiative transfer equation, previous approaches…
We present a general approach to visualizing uncertainty in static 2-D statistical graphics. If we treat a visualization as a function of its underlying quantities, uncertainty in those quantities induces a distribution over images. We show…
Sparse-view computed tomography (CT) can be used to reduce radiation dose greatly but is suffers from severe image artifacts. Recently, the deep learning based method for sparse-view CT reconstruction has attracted a major attention.…
Unsupervised visual anomaly detection from multi-view images presents a significant challenge: distinguishing genuine defects from benign appearance variations caused by viewpoint changes. Existing methods, often designed for single-view…
The increasingly wide use of deep machine learning techniques in computational mechanics has significantly accelerated simulations of problems that were considered unapproachable just a few years ago. However, in critical applications such…
Conventional unsupervised anomaly detection (UAD) methods build separate models for each object category. Recent studies have proposed to train a unified model for multiple classes, namely model-unified UAD. However, such methods still…