Related papers: DKM: Differentiable K-Means Clustering Layer for N…

Compressing convolutional neural networks (CNNs) has received ever-increasing research focus. However, most existing CNN compression methods do not interpret their inherent structures to distinguish the implicit redundancy. In this paper,…

Today's intelligent applications can achieve high performance accuracy using machine learning (ML) techniques, such as deep neural networks (DNNs). Traditionally, in a remote DNN inference problem, an edge device transmits raw data to a…

Deep neural networks (DNNs) have achieved extraordinary performance in solving different tasks in various fields. However, the conventional DNN model is steadily approaching the ground-truth value through loss backpropagation. In some…

The emerging edge-cloud collaborative Deep Learning (DL) paradigm aims at improving the performance of practical DL implementations in terms of cloud bandwidth consumption, response latency, and data privacy preservation. Focusing on…

Deep neural networks (DNN) have achieved remarkable success in computer vision (CV). However, training and inference of DNN models are both memory and computation intensive, incurring significant overhead in terms of energy consumption and…

The success of deep neural networks (DNN) in machine perception applications such as image classification and speech recognition comes at the cost of high computation and storage complexity. Inference of uncompressed large scale DNN models…

Deep learning and especially the use of Deep Neural Networks (DNNs) provides impressive results in various regression and classification tasks. However, to achieve these results, there is a high demand for computing and storing resources.…

Quantization has emerged to be an effective way to significantly boost the performance of deep neural networks (DNNs) by utilizing low-bit computations. Despite having lower numerical precision, quantized DNNs are able to reduce both memory…

Recently, DNN model compression based on network architecture design, e.g., SqueezeNet, attracted a lot attention. No accuracy drop on image classification is observed on these extremely compact networks, compared to well-known models. An…

Unstructured neural network pruning algorithms have achieved impressive compression rates. However, the resulting - typically irregular - sparse matrices hamper efficient hardware implementations, leading to additional memory usage and…

Conditional Maximum Mean Discrepancy (CMMD) can capture the discrepancy between conditional distributions by drawing support from nonlinear kernel functions, thus it has been successfully used for pattern classification. However, CMMD does…

This work proposes a novel Deep Neural Network (DNN) quantization framework, namely RMSMP, with a Row-wise Mixed-Scheme and Multi-Precision approach. Specifically, this is the first effort to assign mixed quantization schemes and multiple…

Motivated by recent work on deep neural network (DNN)-based image compression methods showing potential improvements in image quality, savings in storage, and bandwidth reduction, we propose to perform image understanding tasks such as…

Defocus blur is one kind of blur effects often seen in images, which is challenging to remove due to its spatially variant amount. This paper presents an end-to-end deep learning approach for removing defocus blur from a single image, so as…

Neural Networks accomplish amazing things, but they suffer from computational and memory bottlenecks that restrict their usage. Nowhere can this be better seen than in the mobile space, where specialized hardware is being created just to…

Despite many modern applications of Deep Neural Networks (DNNs), the large number of parameters in the hidden layers makes them unattractive for deployment on devices with storage capacity constraints. In this paper we propose a Data-Driven…

The edge computing paradigm places compute-capable devices - edge servers - at the network edge to assist mobile devices in executing data analysis tasks. Intuitively, offloading compute-intense tasks to edge servers can reduce their…

Recently, the compression and deployment of powerful deep neural networks (DNNs) on resource-limited edge devices to provide intelligent services have become attractive tasks. Although knowledge distillation (KD) is a feasible solution for…

Weight quantization is one of the most important techniques of Deep Neural Networks (DNNs) model compression method. A recent work using systematic framework of DNN weight quantization with the advanced optimization algorithm ADMM…

Neural networks have been notorious for being computationally expensive. This is mainly because neural networks are often over-parametrized and most likely have redundant nodes or layers as they are getting deeper and wider. Their demand…