Related papers: Distinguishing mirror from glass: A 'big data' app…
Deep convolutional neural networks (DCNNs) have attracted much attention recently, and have shown to be able to recognize thousands of object categories in natural image databases. Their architecture is somewhat similar to that of the human…
The classification of random objects within metric spaces without a vector structure has attracted increasing attention. However, the complexity inherent in such non-Euclidean data often restricts existing models to handle only a limited…
Interdisciplinary research is often at the core of scientific progress. This dissertation explores some advantageous synergies between machine learning, cognitive science and neuroscience. In particular, this thesis focuses on vision and…
While recent deep neural networks have achieved a promising performance on object recognition, they rely implicitly on the visual contents of the whole image. In this paper, we train deep neural net- works on the foreground (object) and…
Machine learning for image classification is an active and rapidly developing field. With the proliferation of classifiers of different sizes and different architectures, the problem of choosing the right model becomes more and more…
The world is abundant with diverse materials, each possessing unique surface appearances that play a crucial role in our daily perception and understanding of their properties. Despite advancements in technology enabling the capture and…
Object recognition is a primary function of the human visual system. It has recently been claimed that the highly successful ability to recognise objects in a set of emergent computer vision systems---Deep Convolutional Neural Networks…
Today's computer vision models achieve human or near-human level performance across a wide variety of vision tasks. However, their architectures, data, and learning algorithms differ in numerous ways from those that give rise to human…
Prior research has shown that human perception of similarity differs from mathematical measures in visual comparison tasks, including those involving directed acyclic graphs. This divergence can lead to missed differences and skepticism…
Neuroscientists classify neurons into different types that perform similar computations at different locations in the visual field. Traditional methods for neural system identification do not capitalize on this separation of 'what' and…
Over the last years, advancements in deep learning models for computer vision have led to a dramatic improvement in their image classification accuracy. However, models with a higher accuracy in the task they were trained on do not…
Our understanding of supercooled liquids and glasses has lagged significantly behind that of simple liquids and crystalline solids. This is in part due to the many possibly relevant degrees of freedom that are present due to the disorder…
We consider a machine learning algorithm to detect and identify strong gravitational lenses on sky images. First, we simulate different artificial but very close to reality images of galaxies, stars and strong lenses, using six different…
Supervised learning is ubiquitous in medical image analysis. In this paper we consider the problem of meta-learning -- predicting which methods will perform well in an unseen classification problem, given previous experience with other…
Numerosity perception is foundational to mathematical learning, but its computational bases are strongly debated. Some investigators argue that humans are endowed with a specialized system supporting numerical representation; others argue…
Humans have a remarkably large capacity to store detailed visual information in long-term memory even after a single exposure, as demonstrated by classic experiments in psychology. For example, Standing (1973) showed that humans could…
Despite the tremendous success of deep learning in computer vision, models still fall behind humans in generalizing to new input distributions. Existing benchmarks do not investigate the specific failure points of models by analyzing…
How much does a single image reveal about the environment it was taken in? In this paper, we investigate how much of that information can be retrieved from a foreground object, combined with the background (i.e. the visible part of the…
Computational methods that automatically extract knowledge from data are critical for enabling data-driven materials science. A reliable identification of lattice symmetry is a crucial first step for materials characterization and…
An important milestone for AI is the development of algorithms that can produce drawings that are indistinguishable from those of humans. Here, we adapt the 'diversity vs. recognizability' scoring framework from Boutin et al, 2022 and find…