Related papers: Confidence from Invariance to Image Transformation…

Uncertainty quantification provides quantitative measures on the reliability of candidate solutions of ill-posed inverse problems. Due to their sequential nature, Monte Carlo sampling methods require large numbers of sampling steps for…

We introduce ViewNeRF, a Neural Radiance Field-based viewpoint estimation method that learns to predict category-level viewpoints directly from images during training. While NeRF is usually trained with ground-truth camera poses, multiple…

The ability to acknowledge the inevitable uncertainty in their knowledge and reasoning is a prerequisite for AI systems to be truly truthful and reliable. In this paper, we present a taxonomy of uncertainty specific to vision-language AI…

In this work we evaluate the impact of digitally altered images on the performance of artificial neural networks. We explore factors that negatively affect the ability of an image classification model to produce consistent and accurate…

Contrastive learning has revolutionized the field of computer vision, learning rich representations from unlabeled data, which generalize well to diverse vision tasks. Consequently, it has become increasingly important to explain these…

Face recognition in unconstrained environments such as surveillance, video, and web imagery must contend with extreme variation in pose, blur, illumination, and occlusion, where conventional visual quality metrics fail to predict whether…

Visual counterfactual explanations identify modifications to an image that would change the prediction of a classifier. We propose a set of techniques based on generative models (VAE) and a classifier ensemble directly trained in the latent…

One of the ways to make artificial intelligence more natural is to give it some room for doubt. Two main questions should be resolved in that way. First, how to train a model to estimate uncertainties of its own predictions? And then, what…

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with…

We study how the training data distribution affects confidence and performance in image classification models. We introduce Embedding Density, a model-agnostic framework that estimates prediction confidence by measuring the distance of test…

Reliably detecting when a deployed machine learning model is likely to fail on a given input is crucial for ensuring safe operation. In this work, we propose DECIDER (Debiasing Classifiers to Identify Errors Reliably), a novel approach that…

We introduce a novel framework for AI-generated image detection through epistemic uncertainty, aiming to address critical security concerns in the era of generative models. Our key insight stems from the observation that distributional…

Safety-critical perception systems require both reliable uncertainty quantification and principled abstention mechanisms to maintain safety under diverse operational conditions. We present a novel dual-threshold conformalization framework…

We study the problem of formally verifying individual fairness of decision tree ensembles, as well as training tree models which maximize both accuracy and individual fairness. In our approach, fairness verification and fairness-aware…

We propose a method for automatically answering questions about images by bringing together recent advances from natural language processing and computer vision. We combine discrete reasoning with uncertain predictions by a multi-world…

Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use deep neural networks…

In the last few years, the artifact patterns in fake images synthesized by different generative models have been inconsistent, leading to the failure of previous research that relied on spotting subtle differences between real and fake. In…

Controlling defects in semiconductor processes is important for maintaining yield, improving production cost, and preventing time-dependent critical component failures. Electron beam-based imaging has been used as a tool to survey wafers in…

In image classification tasks, deep learning models are vulnerable to image distortion. For successful deployment, it is important to identify distortion levels under which the model is usable i.e. its accuracy stays above a stipulated…

We introduce a new technique that automatically generates diverse, visually compelling stylizations for a photograph in an unsupervised manner. We achieve this by learning style ranking for a given input using a large photo collection and…