Related papers: SqueezeNext: Hardware-Aware Neural Network Design

The DenseNet architecture is highly computationally efficient as a result of feature reuse. However, a naive DenseNet implementation can require a significant amount of GPU memory: If not properly managed, pre-activation batch normalization…

Real-time semantic segmentation is of significant importance for mobile and robotics related applications. We propose a computationally efficient segmentation network which we term as ShuffleSeg. The proposed architecture is based on…

Driven by improved architectures and better representation learning frameworks, the field of visual recognition has enjoyed rapid modernization and performance boost in the early 2020s. For example, modern ConvNets, represented by ConvNeXt,…

Electrocardiogram (ECG) interpretation is essential for diagnosing a wide range of cardiac abnormalities. While deep learning has shown strong potential for automating ECG classification, many existing models rely on large, computationally…

Nowadays, due to the rapid population expansion, food shortage has become a critical issue. In order to stabilizing the food source production, preventing crops from being attacked by pests is very important. In generally, farmers use…

The enormous and ever-increasing complexity of state-of-the-art neural networks (NNs) has impeded the deployment of deep learning on resource-limited devices such as the Internet of Things (IoTs). Stochastic computing exploits the inherent…

Convolutional neural networks (CNN) have been widely used for boosting the performance of many machine intelligence tasks. However, the CNN models are usually computationally intensive and energy consuming, since they are often designed…

Neural networks are both computationally intensive and memory intensive, making them difficult to deploy on embedded systems. Also, conventional networks fix the architecture before training starts; as a result, training cannot improve the…

Transfer learning is one of the subjects undergoing intense study in the area of machine learning. In object recognition and object detection there are known experiments for the transferability of parameters, but not for neural networks…

In this paper, we explore how to design lightweight CNN architecture for embedded computing systems. We propose L-Mobilenet model for ZYNQ based hardware platform. L-Mobilenet can adapt well to the hardware computing and accelerating, and…

Transfer Learning enables Convolutional Neural Networks (CNN) to acquire knowledge from a source domain and transfer it to a target domain, where collecting large-scale annotated examples is time-consuming and expensive. Conventionally,…

This paper studies the computational offloading of CNN inference in device-edge co-inference systems. Inspired by the emerging paradigm semantic communication, we propose a novel autoencoder-based CNN architecture (AECNN), for effective…

Designing convolutional neural networks (CNN) for mobile devices is challenging because mobile models need to be small and fast, yet still accurate. Although significant efforts have been dedicated to design and improve mobile CNNs on all…

The deployment of deep convolutional neural networks (CNNs) in many real world applications is largely hindered by their high computational cost. In this paper, we propose a novel learning scheme for CNNs to simultaneously 1) reduce the…

Although deep models have greatly improved the accuracy and robustness of image segmentation, obtaining segmentation results with highly accurate boundaries and fine structures is still a challenging problem. In this paper, we propose a…

Over the past few decades, underwater image enhancement has attracted increasing amount of research effort due to its significance in underwater robotics and ocean engineering. Research has evolved from implementing physics-based solutions…

Deep neural networks (DNNs) have achieved significant success in a variety of real world applications, i.e., image classification. However, tons of parameters in the networks restrict the efficiency of neural networks due to the large model…

Non-Local (NL) blocks have been widely studied in various vision tasks. However, it has been rarely explored to embed the NL blocks in mobile neural networks, mainly due to the following challenges: 1) NL blocks generally have heavy…

The large computing and memory cost of deep neural networks (DNNs) often precludes their use in resource-constrained devices. Quantizing the parameters and operations to lower bit-precision offers substantial memory and energy savings for…

Neural networks have become dominant computational workloads across cloud and edge platforms, but their rapid growth in model size and deployment diversity has exposed hardware bottlenecks increasingly dominated by memory movement,…