Related papers: MBS: Macroblock Scaling for CNN Model Reduction
In recent years, single image super-resolution (SR) methods based on deep convolutional neural networks (CNNs) have made significant progress. However, due to the non-adaptive nature of the convolution operation, they cannot adapt to…
Training CNNs from scratch on new domains typically demands large numbers of labeled images and computations, which is not suitable for low-power hardware. One way to reduce these requirements is to modularize the CNN architecture and…
Recently, deep convolutional neural networks (CNNs) have achieved many eye-catching results. However, deploying CNNs on resource-constrained edge devices is constrained by limited memory bandwidth for transmitting large intermediated data…
Neural networks have been extensively applied to a variety of tasks, achieving astounding results. Applying neural networks in the scientific field is an important research direction that is gaining increasing attention. In scientific…
Convolutional Neural Networks have dramatically improved in recent years, surpassing human accuracy on certain problems and performance exceeding that of traditional computer vision algorithms. While the compute pattern in itself is…
Image classification is a fundamental task in computer vision with diverse applications, ranging from autonomous systems to medical imaging. The CIFAR-10 dataset is a widely used benchmark to evaluate the performance of classification…
We present a multigrid-in-channels (MGIC) approach that tackles the quadratic growth of the number of parameters with respect to the number of channels in standard convolutional neural networks (CNNs). Thereby our approach addresses the…
We propose a generalized convolutional neural network (CNN) architecture that first decomposes the input signal into subbands by an adaptive filter bank structure, and then uses convolutional layers to extract features from each subband…
For millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems, hybrid processing architecture is usually used to reduce the complexity and cost, which poses a very challenging issue in channel estimation. In this paper,…
Massive multiple-input multiple-output (MIMO) communication systems have a huge potential both in terms of data rate and energy efficiency, although channel estimation becomes challenging for a large number of antennas. Using a physical…
Neural Architecture Search (NAS) has shifted network design from using human intuition to leveraging search algorithms guided by evaluation metrics. We study channel size optimization in convolutional neural networks (CNN) and identify the…
Neural Architecture Search (NAS) has been pivotal in finding optimal network configurations for Convolution Neural Networks (CNNs). While many methods explore NAS from a global search-space perspective, the employed optimization schemes…
To accelerate deep CNN models, this paper proposes a novel spatially adaptive framework that can dynamically generate pixel-wise sparsity according to the input image. The sparse scheme is pixel-wise refined, regional adaptive under a…
Phenomenally successful in practical inference problems, convolutional neural networks (CNN) are widely deployed in mobile devices, data centers, and even supercomputers. The number of parameters needed in CNNs, however, are often large and…
Shallow Convolution Neural Network (CNN) is a time-tested tool for the information extraction from cancer pathology reports. Shallow CNN performs competitively on this task to other deep learning models including BERT, which holds the…
To address the limitations of existing magnitude-based pruning algorithms in cases where model weights or activations are of large and similar magnitude, we propose a novel perspective to discover parameter redundancy among channels and…
Pruning methods have shown to be effective at reducing the size of deep neural networks while keeping accuracy almost intact. Among the most effective methods are those that prune a network while training it with a sparsity prior loss and…
Convolutional neural networks (CNNs) have achieved remarkable success in image recognition. Although the internal patterns of the input images are effectively learned by the CNNs, these patterns only constitute a small proportion of useful…
As convolutional neural networks (CNNs) enable state-of-the-art computer vision applications, their high energy consumption has emerged as a key impediment to their deployment on embedded and mobile devices. Towards efficient image…
Embedding Convolutional Neural Network (CNN) into edge devices for inference is a very challenging task because such lightweight hardware is not born to handle this heavyweight software, which is the common overhead from the modern…