Related papers: Let's agree to disagree: learning highly debatable…

In many classification tasks, there is no definitive ground truth, only human judgments that may disagree. We address two challenges that arise in such settings: (1) how to use human raters to score classifiers, and (2) how to use them for…

This work deviates from easy-to-define class boundaries for object interactions. For the task of object interaction recognition, often captured using an egocentric view, we show that semantic ambiguities in verbs and recognising…

Owing to the advancement of deep learning, artificial systems are now rival to humans in several pattern recognition tasks, such as visual recognition of object categories. However, this is only the case with the tasks for which correct…

Given multiple datasets with different label spaces, the goal of this work is to train a single object detector predicting over the union of all the label spaces. The practical benefits of such an object detector are obvious and significant…

Perception-related errors comprise most diagnostic mistakes in radiology. To mitigate this problem, radiologists employ personalized and high-dimensional visual search strategies, otherwise known as search patterns. Qualitative descriptions…

This paper focuses on vision-based pose estimation for multiple rigid objects placed in clutter, especially in cases involving occlusions and objects resting on each other. Progress has been achieved recently in object recognition given…

Image classification is often prone to labelling uncertainty. To generate suitable training data, images are labelled according to evaluations of human experts. This can result in ambiguities, which will affect subsequent models. In this…

The human ability to recognize when an object belongs or does not belong to a particular vision task outperforms all open set recognition algorithms. Human perception as measured by the methods and procedures of visual psychophysics from…

With the development of deep learning, medical image classification has been significantly improved. However, deep learning requires massive data with labels. While labeling the samples by human experts is expensive and time-consuming,…

Learning to construct text representations in end-to-end systems can be difficult, as natural languages are highly compositional and task-specific annotated datasets are often limited in size. Methods for directly supervising language…

Current state-of-the-art deep learning systems for visual object recognition and detection use purely supervised training with regularization such as dropout to avoid overfitting. The performance depends critically on the amount of labeled…

Machine learning models are often used to inform real world risk assessment tasks: predicting consumer default risk, predicting whether a person suffers from a serious illness, or predicting a person's risk to appear in court. Given…

Deep neural networks are known to be data-driven and label noise can have a marked impact on model performance. Recent studies have shown great robustness to classic image recognition even under a high noisy rate. In medical applications,…

Many classification problems can be difficult to formulate directly in terms of the traditional supervised setting, where both training and test samples are individual feature vectors. There are cases in which samples are better described…

We consider a classifier whose test set is exposed to various perturbations that are not present in the training set. These test samples still contain enough features to map them to the same class as their unperturbed counterpart. Current…

Classifiers for medical image analysis are often trained with a single consensus label, based on combining labels given by experts or crowds. However, disagreement between annotators may be informative, and thus removing it may not be the…

It is not always possible to recognise objects and infer material properties for a scene from visual cues alone, since objects can look visually similar whilst being made of very different materials. In this paper, we therefore present an…

We address the problem of learning a single model for person re-identification, attribute classification, body part segmentation, and pose estimation. With predictions for these tasks we gain a more holistic understanding of persons, which…

Medical image segmentation annotation suffers from inter-rater variability (IRV) due to differences in annotators' expertise and the inherent blurriness of medical images. Standard approaches that simply average expert labels are flawed, as…

Visually identifying materials is crucial for many tasks, yet material perception remains poorly understood. Distinguishing mirror from glass is particularly challenging as both materials derive their appearance from their surroundings, yet…