相关论文: High Performance Depthwise and Pointwise Convoluti…

Depthwise convolution has gradually become an indispensable operation for modern efficient neural networks and larger kernel sizes ($\ge5$) have been applied to it recently. In this paper, we propose a novel extremely separated…

High-end mobile platforms rapidly serve as primary computing devices for a wide range of Deep Neural Network (DNN) applications. However, the constrained computation and storage resources on these devices still pose significant challenges…

Recent research on vision backbone architectures has predominantly focused on optimizing efficiency for hardware platforms with high parallel processing capabilities. This category increasingly includes embedded systems such as mobile…

Convolution is the core component within deep neural networks and it is computationally intensive and time consuming. Tensor data layouts significantly impact convolution operations in terms of memory access and computational efficiency.…

We introduce Dynamic Mobile-Former(DMF), maximizes the capabilities of dynamic convolution by harmonizing it with efficient operators.Our Dynamic MobileFormer effectively utilizes the advantages of Dynamic MobileNet (MobileNet equipped with…

Recent years have witnessed the great success of deep convolutional neural networks (CNNs) in image denoising. Albeit deeper network and larger model capacity generally benefit performance, it remains a challenging practical issue to train…

Deep Separable Convolutional Neural Networks (DSCNNs) have become the emerging paradigm by offering modular networks with structural sparsity in order to achieve higher accuracy with relatively lower operations and parameters. However,…

We propose model with larger spatial size of feature maps and evaluate it on object detection task. With the goal to choose the best feature extraction network for our model we compare several popular lightweight networks. After that we…

Deep learning-based speech enhancement methods have significantly improved speech quality and intelligibility. Convolutional neural networks (CNNs) have been proven to be essential components of many high-performance models. In this paper,…

Transformer and its variants have shown great potential for various vision tasks in recent years, including image classification, object detection and segmentation. Meanwhile, recent studies also reveal that with proper architecture design,…

Convolutional layers are one of the basic building blocks of modern deep neural networks. One fundamental assumption is that convolutional kernels should be shared for all examples in a dataset. We propose conditionally parameterized…

Deep neural networks face numerous challenges in hyperspectral image classification, including high-dimensional data, sparse ground object distributions, and spectral redundancy, which often lead to classification overfitting and limited…

Multi cast communication is a key technology for wireless mesh networks. Multicast provides efficient data distribution among a group of nodes, Generally sensor networks and MANETs uses multicast algorithms which are designed to be energy…

When deploying a deep neural network on constrained hardware, it is possible to replace the network's standard convolutions with grouped convolutions. This allows for substantial memory savings with minimal loss of accuracy. However,…

Deep neural networks (DNNs) have achieved unprecedented success in the field of artificial intelligence (AI), including computer vision, natural language processing and speech recognition. However, their superior performance comes at the…

Videos take a lot of time to transport over the network, hence running analytics on the live video on embedded or mobile devices has become an important system driver. Considering that such devices, e.g., surveillance cameras or AR/VR…

This work is motivated by recent developments in Deep Neural Networks, particularly the Transformer architectures underlying applications such as ChatGPT, and the need for performing inference on mobile devices. Focusing on emerging…

When training early-stage deep neural networks (DNNs), generating intermediate features via convolution or linear layers occupied most of the execution time. Accordingly, extensive research has been done to reduce the computational burden…

The Winograd or Cook-Toom class of algorithms help to reduce the overall compute complexity of many modern deep convolutional neural networks (CNNs). Although there has been a lot of research done on model and algorithmic optimization of…

Positron range (PR) blurring degrades positron emission tomography (PET) image resolution, particularly for high-energy emitters like gallium-68 (68 Ga). We introduce Dual-Input Dynamic Convolution (DDConv), a novel computationally…