Related papers: Spontaneous segregation of visual information betw…

Understanding the inner workings of deep neural networks (DNNs) is essential to provide trustworthy artificial intelligence techniques for practical applications. Existing studies typically involve linking semantic concepts to units or…

The informational synthesis of neural structures, processes, parameters and characteristics that allow a unified description and modeling as neural machines of natural and artificial neural systems is presented. The general informational…

Although deep feedforward neural networks share some characteristics with the primate visual system, a key distinction is their dynamics. Deep nets typically operate in serial stages wherein each layer completes its computation before…

We discuss relations between Residual Networks (ResNet), Recurrent Neural Networks (RNNs) and the primate visual cortex. We begin with the observation that a special type of shallow RNN is exactly equivalent to a very deep ResNet with…

Understanding the encoding and decoding mechanisms of dynamic neural responses to different visual stimuli is an important topic in exploring how the brain represents visual information. Currently, hierarchically deep neural networks (DNNs)…

Recent advances of semantic image segmentation greatly benefit from deeper and larger Convolutional Neural Network (CNN) models. Compared to image segmentation in the wild, properties of both medical images themselves and of existing…

The automated analysis of microscopy images is a challenge in the context of single-cell tracking and quantification. This work has as goals the study of the performance of deep learning for segmenting microscopy images and the improvement…

Neural networks are prone to learning shortcuts -- they often model simple correlations, ignoring more complex ones that potentially generalize better. Prior works on image classification show that instead of learning a connection to object…

Learning and inferring features that generate sensory input is a task continuously performed by cortex. In recent years, novel algorithms and learning rules have been proposed that allow neural network models to learn such features from…

Symmetry is present in nature and science. In image processing, kernels for spatial filtering possess some symmetry (e.g. Sobel operators, Gaussian, Laplacian). Convolutional layers in artificial feed-forward neural networks have typically…

A number of scientists suggested that human visual perception may emerge from image statistics, shaping efficient neural representations in early vision. In this work, a bio-inspired architecture that can accommodate several known facts in…

Traditional computer graphics rendering pipeline is designed for procedurally generating 2D quality images from 3D shapes with high performance. The non-differentiability due to discrete operations such as visibility computation makes it…

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with…

The complex multi-stage architecture of cortical visual pathways provides the neural basis for efficient visual object recognition in humans. However, the stage-wise computations therein remain poorly understood. Here, we compared temporal…

Graph convolutional learning has led to many exciting discoveries in diverse areas. However, in some applications, traditional graphs are insufficient to capture the structure and intricacies of the data. In such scenarios, multigraphs…

In this paper, we present contemporary techniques for visualising the feature space of a deep learning image classification neural network. These techniques are viewed in the context of a feed-forward network trained to classify low…

Computational models of vision have traditionally been developed in a bottom-up fashion, by hierarchically composing a series of straightforward operations - i.e. convolution and pooling - with the aim of emulating simple and complex cells…

Since the study of deep convolutional neural network became prevalent, one of the important discoveries is that a feature map from a convolutional network can be extracted before going into the fully connected layer and can be used as a…

Rapid categorization paradigms have a long history in experimental psychology: Characterized by short presentation times and speedy behavioral responses, these tasks highlight the efficiency with which our visual system processes natural…

Visualizations often encode multivariate data by mapping attributes to distinct visual channels such as color, size, or shape. The effectiveness of these encodings depends on separability--the extent to which channels can be perceived…