Related papers: Color Cerberus
Proving for triangulations an extended version of the 4-colour theorem by induction, we manage to exclude the case which led to the failure of Kempe's attempted proof. The new idea is to claim the existence of a "nice" 4-colouring, in which…
Human beings can imagine the colours of a grayscale image with no particular effort thanks to their ability of semantic feature extraction. Can an autonomous system achieve that? Can it hallucinate plausible and vibrant colours? This is the…
Deep networks have become very popular over the past few years. The main reason for this widespread use is their excellent ability to learn and predict knowledge in a very easy and efficient way. Convolutional neural networks and…
Multi-illuminant color constancy methods aim to eliminate local color casts within an image through pixel-wise illuminant estimation. Existing methods mainly employ deep learning to establish a direct mapping between an image and its…
The impressive performance of Convolutional Neural Networks (CNNs) when solving different vision problems is shadowed by their black-box nature and our consequent lack of understanding of the representations they build and how these…
It has been argued that semantic systems reflect pressure for efficiency, and a current debate concerns the cultural evolutionary process that produces this pattern. We consider efficiency as instantiated in the Information Bottleneck (IB)…
Deep learning (DL) has revolutionized many fields such as materials design and protein folding. Recent studies have demonstrated the advantages of DL in the inverse design of structural colors, by effectively learning the complex nonlinear…
The classical Weisfeiler-Leman algorithm aka color refinement is fundamental for graph learning with kernels and neural networks. Originally developed for graph isomorphism testing, the algorithm iteratively refines vertex colors. On many…
Following the surge of popularity of Transformers in Computer Vision, several studies have attempted to determine whether they could be more robust to distribution shifts and provide better uncertainty estimates than Convolutional Neural…
Deep neural networks exhibit remarkable performance, yet their black-box nature limits their utility in fields like healthcare where interpretability is crucial. Existing explainability approaches often sacrifice accuracy and lack…
We investigate multiple techniques to improve upon the current state of the art deep convolutional neural network based image classification pipeline. The techiques include adding more image transformations to training data, adding more…
Recently, convolutional neural networks (CNNs) have been used as a powerful tool to solve many problems of machine learning and computer vision. In this paper, we aim to provide insight on the property of convolutional neural networks, as…
Neural networks have enabled state-of-the-art approaches to achieve incredible results on computer vision tasks such as object detection. However, such success greatly relies on costly computation resources, which hinders people with cheap…
Consistency regularization describes a class of approaches that have yielded state-of-the-art results for semi-supervised classification. While semi-supervised semantic segmentation proved to be more challenging, a number of successful…
A biologically plausible computational model for color representation is introduced. We present a mechanistic hierarchical model of neurons that not only successfully encodes local hue, but also explicitly reveals how the contributions of…
As a novel method eliminating chromatic aberration on objects, computational color constancy has becoming a fundamental prerequisite for many computer vision applications. Among algorithms performing this task, the learning-based ones have…
Major winning Convolutional Neural Networks (CNNs), such as AlexNet, VGGNet, ResNet, GoogleNet, include tens to hundreds of millions of parameters, which impose considerable computation and memory overhead. This limits their practical use…
We propose contextual convolution (CoConv) for visual recognition. CoConv is a direct replacement of the standard convolution, which is the core component of convolutional neural networks. CoConv is implicitly equipped with the capability…
In this paper, a learning-free color constancy algorithm called the Patch-wise Bright Pixels (PBP) is proposed. In this algorithm, an input image is first downsampled and then cut equally into a few patches. After that, according to the…
Image signal processors (ISPs) are historically grown legacy software systems for reconstructing color images from noisy raw sensor measurements. They are usually composited of many heuristic blocks for denoising, demosaicking, and color…