Related papers: MG3MConv: Multi-Grained Matrix-Multiplication-Mapp…
Despite the remarkable success of deep learning, an optimal convolution operation on point clouds remains elusive owing to their irregular data structure. Existing methods mainly focus on designing an effective continuous kernel function…
Mixed-precision neural network (MPNN) that utilizes just enough data width for the neural network processing is an effective approach to meet the stringent resources constraints including memory and computing of MCUs. Nevertheless, there is…
The existing 3D deep learning methods adopt either individual point-based features or local-neighboring voxel-based features, and demonstrate great potential for processing 3D data. However, the point based models are inefficient due to the…
There has been exploding interest in embracing Transformer-based architectures for medical image segmentation. However, the lack of large-scale annotated medical datasets make achieving performances equivalent to those in natural images…
Quantization for Convolutional Neural Network (CNN) has shown significant progress with the intention of reducing the cost of computation and storage with low-bitwidth data inputs. There are, however, no systematic studies on how an…
Convolutional Neural Networks (CNN) are becoming a common presence in many applications and services, due to their superior recognition accuracy. They are increasingly being used on mobile devices, many times just by porting large models…
The analysis of 3D point clouds has diverse applications in robotics, vision and graphics. Processing them presents specific challenges since they are naturally sparse, can vary in spatial resolution and are typically unordered. Graph-based…
In deep learning frameworks, weight pruning is a widely used technique for improving computational efficiency by reducing the size of large models. This is especially critical for convolutional operators, which often act as performance…
Extracting features from a huge amount of data for object recognition is a challenging task. Convolution neural network can be used to meet the challenge, but it often requires a large number of computation resources. In this paper, a…
We introduce convolutional multi-hybrid architectures, with a design grounded on two simple observations. First, operators in hybrid models can be tailored to token manipulation tasks such as in-context recall, multi-token recall, and…
A low-power precision-scalable processor for ConvNets or convolutional neural networks (CNN) is implemented in a 40nm technology. Its 256 parallel processing units achieve a peak 102GOPS running at 204MHz. To minimize energy consumption…
Modern efficient Convolutional Neural Networks(CNNs) always use Depthwise Separable Convolutions(DSCs) and Neural Architecture Search(NAS) to reduce the number of parameters and the computational complexity. But some inherent…
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…
Quantization for CNN has shown significant progress with the intention of reducing the cost of computation and storage with low-bitwidth data representations. There are, however, no systematic studies on how an existing full-bitwidth…
Convolutional Neural Networks (CNNs) have been regarded as the go-to models for visual recognition. More recently, convolution-free networks, based on multi-head self-attention (MSA) or multi-layer perceptrons (MLPs), become more and more…
Depthwise convolution is becoming increasingly popular in modern efficient ConvNets, but its kernel size is often overlooked. In this paper, we systematically study the impact of different kernel sizes, and observe that combining the…
Semantic Segmentation using deep convolutional neural network pose more complex challenge for any GPU intensive task. As it has to compute million of parameters, it results to huge memory consumption. Moreover, extracting finer features and…
This paper considers a convolutional neural network transformation that reduces computation complexity and thus speedups neural network processing. Usage of convolutional neural networks (CNN) is the standard approach to image recognition…
Graph Convolutional Networks (GCNs) have made significant advances in semi-supervised learning, especially for classification tasks. However, existing GCN based methods have two main drawbacks. First, to increase the receptive field and…
As the development of deep neural networks, 3D object recognition is becoming increasingly popular in computer vision community. Many multi-view based methods are proposed to improve the category recognition accuracy. These approaches…