Related papers: Model Rubik's Cube: Twisting Resolution, Depth and…
While the depth of convolutional neural networks has attracted substantial attention in the deep learning research, the width of these networks has recently received greater interest. The width of networks, defined as the size of the…
To design fast neural networks, many works have been focusing on reducing the number of floating-point operations (FLOPs). We observe that such reduction in FLOPs, however, does not necessarily lead to a similar level of reduction in…
Deep neural networks give state-of-the-art accuracy for reconstructing images from few and noisy measurements, a problem arising for example in accelerated magnetic resonance imaging (MRI). However, recent works have raised concerns that…
Structural pruning of neural network parameters reduces computation, energy, and memory transfer costs during inference. We propose a novel method that estimates the contribution of a neuron (filter) to the final loss and iteratively…
In this work we develop a novel approach using deep neural networks to reconstruct the conductivity distribution in elliptic problems from one measurement of the solution over the whole domain. The approach is based on a mixed reformulation…
Network pruning reduces the computation costs of an over-parameterized network without performance damage. Prevailing pruning algorithms pre-define the width and depth of the pruned networks, and then transfer parameters from the unpruned…
The deployment of deep neural networks in real-world applications is mostly restricted by their high inference costs. Extensive efforts have been made to improve the accuracy with expert-designed or algorithm-searched architectures.…
We propose a new method for creating computationally efficient and compact convolutional neural networks (CNNs) using a novel sparse connection structure that resembles a tree root. This allows a significant reduction in computational cost…
Neural network pruning reduces the computational cost of an over-parameterized network to improve its efficiency. Popular methods vary from $\ell_1$-norm sparsification to Neural Architecture Search (NAS). In this work, we propose a novel…
Model compression techniques allow to significantly reduce the computational cost associated with data processing by deep neural networks with only a minor decrease in average accuracy. Simultaneously, reducing the model size may have a…
It has become mainstream in computer vision and other machine learning domains to reuse backbone networks pre-trained on large datasets as preprocessors. Typically, the last layer is replaced by a shallow learning machine of sorts; the…
Automatic designing computationally efficient neural networks has received much attention in recent years. Existing approaches either utilize network pruning or leverage the network architecture search methods. This paper presents a new…
The rapid growth in complexity and size of modern deep neural networks (DNNs) has increased challenges related to computational costs and memory usage, spurring a growing interest in efficient model compression techniques. Previous…
In this work, we propose an effective scheme (called DP-Net) for compressing the deep neural networks (DNNs). It includes a novel dynamic programming (DP) based algorithm to obtain the optimal solution of weight quantization and an…
A family of super deep networks, referred to as residual networks or ResNet, achieved record-beating performance in various visual tasks such as image recognition, object detection, and semantic segmentation. The ability to train very deep…
With the good performance of deep learning algorithms in the field of computer vision (CV), the convolutional neural network (CNN) architecture has become a main backbone of the computer vision task. With the widespread use of mobile…
Efficient deep learning-based approaches have achieved remarkable performance in single image super-resolution. However, recent studies on efficient super-resolution have mainly focused on reducing the number of parameters and…
One of the most pressing challenges prevalent in the steel manufacturing industry is the identification of surface defects. Early identification of casting defects can help boost performance, including streamlining production processes.…
Convolutional Neural Networks (ConvNets) have successfully contributed to improve the accuracy of regression-based methods for computer vision tasks such as human pose estimation, landmark localization, and object detection. The network…
Convolutional Neural Networks (CNNs) have a large number of parameters and take significantly large hardware resources to compute, so edge devices struggle to run high-level networks. This paper proposes a novel method to reduce the…