Related papers: Human eye inspired log-polar pre-processing for ne…
The Expanding Hole Illusion is a compelling visual phenomenon in which a static, concentric pattern evokes a strong perception of continuous forward motion. Despite its simplicity, this illusion challenges our understanding of how the brain…
This paper presents a new framework for human body part segmentation based on Deep Convolutional Neural Networks trained using only synthetic data. The proposed approach achieves cutting-edge results without the need of training the models…
In this work, we develop convolutional neural generative coding (Conv-NGC), a generalization of predictive coding to the case of convolution/deconvolution-based computation. Specifically, we concretely implement a flexible…
In the last ten years, Convolutional Neural Networks (CNNs) have formed the basis of deep-learning architectures for most computer vision tasks. However, they are not necessarily optimal. For example, mathematical morphology is known to be…
The human visual system uses two parallel pathways for spatial processing and object recognition. In contrast, computer vision systems tend to use a single feedforward pathway, rendering them less robust, adaptive, or efficient than human…
Despite the effectiveness of Convolutional Neural Networks (CNNs) for image classification, our understanding of the relationship between shape of convolution kernels and learned representations is limited. In this work, we explore and…
Neuromorphic vision made significant progress in recent years, thanks to the natural match between spiking neural networks and event data in terms of biological inspiration, energy savings, latency and memory use for dynamic visual data…
As neural networks grow larger and more complex and data-hungry, training costs are skyrocketing. Especially when lifelong learning is necessary, such as in recommender systems or self-driving cars, this might soon become unsustainable. In…
We propose Neural Image Compression (NIC), a two-step method to build convolutional neural networks for gigapixel image analysis solely using weak image-level labels. First, gigapixel images are compressed using a neural network trained in…
Convolutional Neural Networks have revolutionized vision applications. There are image domains and representations, however, that cannot be handled by standard CNNs (e.g., spherical images, superpixels). Such data are usually processed…
Convolutional neural networks (CNNs) are widely used for image recognition and text analysis, and have been suggested for application on one-dimensional data as a way to reduce the need for pre-processing steps. Pre-processing is an…
Currently, increasingly deeper neural networks have been applied to improve their accuracy. In contrast, We propose a novel wider Convolutional Neural Networks (CNN) architecture, motivated by the Multi-column Deep Neural Networks and the…
Rotation invariance has been studied in the computer vision community primarily in the context of small in-plane rotations. This is usually achieved by building invariant image features. However, the problem of achieving invariance for…
Automated design methods for convolutional neural networks (CNNs) have recently been developed in order to increase the design productivity. We propose a neuroevolution method capable of evolving and optimizing CNNs with respect to the…
Sub-10cm diameter nano-drones are gaining momentum thanks to their applicability in scenarios prevented to bigger flying drones, such as in narrow environments and close to humans. However, their tiny form factor also brings their major…
It is arguable that whether the single camera captured (monocular) image datasets are sufficient enough to train and test convolutional neural networks (CNNs) for imitating the biological neural network structures of the human brain. As…
Convolutional neural networks (CNNs) have achieved great success in natural image saliency prediction. The primary goal of this study is to investigate the performance of saliency prediction in CNN and classic models with psychophysical…
We introduce Natural Learning (NL), a novel algorithm that elevates the explainability and interpretability of machine learning to an extreme level. NL simplifies decisions into intuitive rules, like "We rejected your loan because your…
In an attempt to follow biological information representation and organization principles, the field of neuromorphic engineering is usually approached bottom-up, from the biophysical models to large-scale integration in silico. While ideal…
In parallel with the success of CNNs to solve vision problems, there is a growing interest in developing methodologies to understand and visualize the internal representations of these networks. How the responses of a trained CNN encode the…