Related papers: RFC-HyPGCN: A Runtime Sparse Feature Compress Acce…

The shared topology of human skeletons motivated the recent investigation of graph convolutional network (GCN) solutions for action recognition. However, most of the existing GCNs rely on the binary connection of two neighboring vertices…

Weight pruning is a technique to make Deep Neural Network (DNN) inference more computationally efficient by reducing the number of model parameters over the course of training. However, most weight pruning techniques generally does not…

Current transformer accelerators primarily focus on optimizing self-attention due to its quadratic complexity. However, this focus is less relevant for vision transformers with short token lengths, where the Feed-Forward Network (FFN) tends…

Model compression techniques on Deep Neural Network (DNN) have been widely acknowledged as an effective way to achieve acceleration on a variety of platforms, and DNN weight pruning is a straightforward and effective method. There are…

Graph convolutional networks (GCNs) have been very successful in modeling non-Euclidean data structures, like sequences of body skeletons forming actions modeled as spatio-temporal graphs. Most GCN-based action recognition methods use deep…

The emergence of deep and large-scale spiking neural networks (SNNs) exhibiting high performance across diverse complex datasets has led to a need for compressing network models due to the presence of a significant number of redundant…

Convolutional neural network (CNN) accelerators are being widely used for their efficiency, but they require a large amount of memory, leading to the use of a slow and power consuming external memory. This paper exploits two schemes to…

The combination of the traditional convolutional network (i.e., an auto-encoder) and the graph convolutional network has attracted much attention in clustering, in which the auto-encoder extracts the node attribute feature and the graph…

Convolutional neural networks (CNNs) demonstrate excellent performance in various computer vision applications. In recent years, FPGA-based CNN accelerators have been proposed for optimizing performance and power efficiency. Most…

Deep convolutional neural networks (CNN) are widely used in modern artificial intelligence (AI) and smart vision systems but also limited by computation latency, throughput, and energy efficiency on a resource-limited scenario, such as…

In this paper, we aim at improving the computational efficiency of graph convolutional networks (GCNs) for learning on point clouds. The basic graph convolution that is typically composed of a $K$-nearest neighbor (KNN) search and a…

Convolutional Neural Networks (CNNs) are hard to deploy on edge devices due to its high computation and storage complexities. As a common practice for model compression, network pruning consists of two major categories: unstructured and…

Graph convolution networks (GCNs) are currently mainstream in learning with irregular data. These models rely on message passing and attention mechanisms that capture context and node-to-node relationships. With multi-head attention, GCNs…

Recent advances in event camera research emphasize processing data in its original sparse form, which allows the use of its unique features such as high temporal resolution, high dynamic range, low latency, and resistance to image blur. One…

While Convolutional Neural Networks (CNNs) excel at learning complex latent-space representations, their over-parameterization can lead to overfitting and reduced performance, particularly with limited data. This, alongside their high…

Inference for Deep Neural Networks is increasingly being executed locally on mobile and embedded platforms due to its advantages in latency, privacy and connectivity. Since modern System on Chips typically execute a combination of different…

3D Gaussian Splatting (3DGS) has emerged as a leading neural rendering technique for high-fidelity view synthesis, prompting the development of dedicated 3DGS accelerators for resource-constrained platforms. The conventional decoupled…

Graph convolutional networks (GCNs) have well-documented performance in various graph learning tasks, but their analysis is still at its infancy. Graph scattering transforms (GSTs) offer training-free deep GCN models that extract features…

Graph Convolutional Networks (GCNs) have emerged as the state-of-the-art method for graph-based learning tasks. However, training GCNs at scale is still challenging, hindering both the exploration of more sophisticated GCN architectures and…

Network compression techniques have become increasingly important in recent years because the loads of Deep Neural Networks (DNNs) are heavy for edge devices in real-world applications. While many methods compress neural network parameters,…