Related papers: Computational role of eccentricity dependent corti…
Humans perceive their surroundings in great detail even though most of our visual field is reduced to low-fidelity color-deprived (e.g. dichromatic) input by the retina. In contrast, most deep learning architectures are computationally…
The evolution of occupied volume under progressive fragmentation of granular matter is studied using a purely geometric model. Rather than modelling disorder directly, properties are investigated by analysing highly ordered reference…
There has been great progress in understanding of anatomical and functional microcircuitry of the primate cortex. However, the fundamental principles of cortical computation - the principles that allow the visual cortex to bind retinal…
The interpretation of cosmological observations relies on a notion of an average Universe, which is usually considered as the homogeneous and isotropic Friedmann-Lema\^itre-Robertson-Walker (FLRW) model. However, inhomogeneities may…
Pooling is a ubiquitous operation in image processing algorithms that allows for higher-level processes to collect relevant low-level features from a region of interest. Currently, max-pooling is one of the most commonly used operators in…
We make progress towards an analytical understanding of the regime of validity of perturbation theory for large scale structures and the nature of some non-perturbative corrections. We restrict ourselves to 1D gravitational collapse, for…
Large scale structure surveys will likely become the next leading cosmological probe. In our universe, matter perturbations are large on short distances and small at long scales, i.e. strongly coupled in the UV and weakly coupled in the IR.…
Monte Carlo simulations are employed to investigate the surface growth generated by deposition of particles of different sizes on a substrate, in one and two dimensions. The particles have a linear form, and occupy an integer number of…
The immense computational cost of simulating turbulence has motivated the use of machine learning approaches for super-resolving turbulent flows. A central challenge is ensuring that learned models respect physical symmetries, such as…
Recent studies show that Vision Transformers(ViTs) exhibit strong robustness against various corruptions. Although this property is partly attributed to the self-attention mechanism, there is still a lack of systematic understanding. In…
Motion compensated prediction is central to the efficiency of video compression. Its predictive coding scheme propagates the quantization distortion through the prediction chain and creates a temporal dependency. Prior research typically…
Neurons in the visual cortex are correlated in their variability. The presence of correlation impacts cortical processing because noise cannot be averaged out over many neurons. In an effort to understand the functional purpose of…
Supernovae observations strongly support the presence of a cosmological constant, but its value, which we will call apparent, is normally determined assuming that the Universe can be accurately described by a homogeneous model. Even in the…
Cosmological linear perturbation theory predicts that the peculiar velocity $V(x)$ and the matter overdensity $\delta(x)$ at a same point $x$ are statistically independent quantities, as log as the initial density fluctuations are random…
Mamba-based vision models have gained extensive attention as a result of being computationally more efficient than attention-based models. However, spatial redundancy still exists in these models, represented by token and block redundancy.…
Object pose estimation is a long-standing problem in computer vision. Recently, attention-based vision transformer models have achieved state-of-the-art results in many computer vision applications. Exploiting the permutation-invariant…
In this position paper, we consider the state of computer vision research with respect to invariance to the horizontal orientation of an image -- what we term reflection invariance. We describe why we consider reflection invariance to be an…
Recently, text-to-image generation with diffusion models has made significant advancements in both higher fidelity and generalization capabilities compared to previous baselines. However, generating holistic multi-view consistent images…
Despite decades of progress, a truly input-size agnostic visual encoder-a fundamental characteristic of human vision-has remained elusive. We address this limitation by proposing \textbf{MambaEye}, a novel, causal sequential encoder that…
We have calculated the absorption characteristics of different hybrid systems consisting of Ag, Ag2 or Ag3 atomic clusters and poly(methacrylic acid) (PMAA) using the time-dependent density-functional theory. The polymer is found to have an…