Related papers: Prediction of Dashed Caf\'e Wall illusion by the C…
Open-cell graphitic foams were fabricated by chemical vapor deposition using nickel templates and their compressive responses were measured over a range of relative densities. The mechanical response required an interpretation in terms of a…
The performance of autonomous systems heavily relies on their ability to generate a robust representation of the environment. Deep neural networks have greatly improved vision-based perception systems but still fail in challenging…
Because of the variabilities of real-world image structures under the natural image transformations that arise when observing similar objects or spatio-temporal events under different viewing conditions, the receptive field responses…
Contrastive learning has shown promising potential for learning robust representations by utilizing unlabeled data. However, constructing effective positive-negative pairs for contrastive learning on facial behavior datasets remains…
We show that variants of the classical reflection functors from quiver representation theory exist in any abstract stable homotopy theory, making them available for example over arbitrary ground rings, for quasi-coherent modules on schemes,…
We initiate a study of cosmology within the framework of Maldacena's AdS/CFT correspondence. We present a comprehensive analysis of the classical motion of a charged domain wall that separates an external Reissner-Nordstrom region of…
We consider the harmonic crystal on the d-dimensional lattice, d larger or equal to 3, that is the centered Gaussian field $\phi$ with covariance given by the Green function of the simple random walk on $Z^d$. Our main aim is to obtain…
In modern computer vision, the optimal representation of 3D shape continues to be task-dependent. One fundamental operation applied to such representations is differentiable rendering, as it enables inverse graphics approaches in learning…
*Concept-based explanations* offer a promising approach for explaining the predictions of deep neural networks in terms of high-level, human-understandable concepts. However, existing methods either do not establish a causal connection…
Graph contrastive learning (GCL) learns node and graph representations by contrasting multiple views of the same graph. Existing methods typically rely on fixed, handcrafted views-usually a local and a global perspective, which limits their…
This work assesses a classical density functional theory (DFT) model for predicting macroscopic static contact angles of pure substances and mixtures by comparison to own experimental data. We employ a DFT with a Helmholtz energy functional…
Understanding human motion processing is essential for building reliable, human-centered computer vision systems. Although deep neural networks (DNNs) achieve strong performance in optical flow estimation, they remain less robust than…
CAM-based methods are widely-used post-hoc interpretability method that produce a saliency map to explain the decision of an image classification model. The saliency map highlights the important areas of the image relevant to the…
Toda Conformal Field Theories (CFTs hereafter) are generalizations of Liouville CFT where the underlying field is no longer scalar but takes values in a finite-dimensional vector space induced by a complex simple Lie algebra. The goal of…
Deep neural networks have significantly improved the performance of low-level vision tasks but also increased the difficulty of interpretability. A deep understanding of deep models is beneficial for both network design and practical…
The fundamental problem of causal inference - that the counterfactual outcome for any individual is never observed - has shaped the entire methodology of the field. Every existing approach substitutes assumptions for missing data:…
We study characteristics of receptive fields of units in deep convolutional networks. The receptive field size is a crucial issue in many visual tasks, as the output must respond to large enough areas in the image to capture information…
When observing the surface patterns of objects delimited by smooth surfaces, the projections of the surface patterns to the image domain will be subject to substantial variabilities, as induced by variabilities in the geometric viewing…
Receptive field profiles registered by cell recordings have shown that mammalian vision has developed receptive fields tuned to different sizes and orientations in the image domain as well as to different image velocities in space-time.…
Neural networks represent data as projections on trained weights in a high dimensional manifold. The trained weights act as a knowledge base consisting of causal class dependencies. Inference built on features that identify these…