Related papers: Belief decision support and reject for textured im…

Image-to-image translation is affected by entanglement phenomena, which may occur in case of target data encompassing occlusions such as raindrops, dirt, etc. Our unsupervised model-based learning disentangles scene and occlusions, while…

Binary classification is one of the most common problem in machine learning. It consists in predicting whether a given element belongs to a particular class. In this paper, a new algorithm for binary classification is proposed using a…

Accurate image classification given small amounts of labelled data (few-shot classification) remains an open problem in computer vision. In this work we examine how the known texture bias of Convolutional Neural Networks (CNNs) affects…

Integrated interpretability without sacrificing the prediction accuracy of decision making algorithms has the potential of greatly improving their value to the user. Instead of assigning a label to an image directly, we propose to learn…

The deployment of Machine Learning models intraoperatively for tissue characterisation can assist decision making and guide safe tumour resections. For image classification models, pixel attribution methods are popular to infer…

Neural networks for computer vision extract uninterpretable features despite achieving high accuracy on benchmarks. In contrast, humans can explain their predictions using succinct and intuitive descriptions. To incorporate explainability…

The investigation of uncertainty is of major importance in risk-critical applications, such as medical image segmentation. Belief function theory, a formal framework for uncertainty analysis and multiple evidence fusion, has made…

A key issue in critical contexts such as medical diagnosis is the interpretability of the deep learning models adopted in decision-making systems. Research in eXplainable Artificial Intelligence (XAI) is trying to solve this issue. However,…

While many unsupervised learning models focus on one family of tasks, either generative or discriminative, we explore the possibility of a unified representation learner: a model which uses a single pre-training stage to address both…

Photometric differences are widely used as supervision signals to train neural networks for estimating depth and camera pose from unlabeled monocular videos. However, this approach is detrimental for model optimization because occlusions…

Statistical models of natural stimuli provide an important tool for researchers in the fields of machine learning and computational neuroscience. A canonical way to quantitatively assess and compare the performance of statistical models is…

Classifying images with an interpretable decision-making process is a long-standing problem in computer vision. In recent years, Prototypical Part Networks has gained traction as an approach for self-explainable neural networks, due to…

Convolutional Neural Networks have demonstrated dermatologist-level performance in the classification of melanoma from skin lesion images, but prediction irregularities due to biases seen within the training data are an issue that should be…

Comprehensive semantic segmentation is one of the key components for robust scene understanding and a requirement to enable autonomous driving. Driven by large scale datasets, convolutional neural networks show impressive results on this…

Deep neural networks can be effective means to automatically classify aerial images but is easy to overfit to the training data. It is critical for trained neural networks to be robust to variations that exist between training and test…

Local discriminative representation is needed in many medical image analysis tasks such as identifying sub-types of lesion or segmenting detailed components of anatomical structures. However, the commonly applied supervised representation…

A major prerequisite for the application of machine learning models in clinical decision making is trust and interpretability. Current explainability studies in the neuroimaging community have mostly focused on explaining individual…

We investigate the ability of a local bi-orthogonal decomposition to build texture segmentation of images. Using the structures associated to the local decomposition of the image independent row and columns we perform a segmentation, where…

Trust in predictions made by machine learning models is increased if the model generalizes well on previously unseen samples and when inference is accompanied by cogent explanations of the reasoning behind predictions. In the image…

Deep neural networks have demonstrated promising performance on image recognition tasks. However, they may heavily rely on confounding factors, using irrelevant artifacts or bias within the dataset as the cue to improve performance. When a…