Related papers: High Performance Depthwise and Pointwise Convoluti…

Lightweight convolutional and transformer-based networks are increasingly preferred for real-time image classification, especially on resource-constrained devices. This study evaluates the impact of hyperparameter optimization on the…

In recent years, diverging-wave (DW) ultrasound imaging has become a very promising methodology for cardiovascular imaging due to its high temporal resolution. However, if they are limited in number, DW transmits provide lower image quality…

Dynamic convolution achieves better performance for efficient CNNs at the cost of negligible FLOPs increase. However, the performance increase can not match the significantly expanded number of parameters, which is the main bottleneck in…

In order to handle modern convolutional neural networks (CNNs) efficiently, a hardware architecture of CNN inference accelerator is proposed to handle depthwise convolutions and regular convolutions, which are both essential building blocks…

Almost in every heavily computation-dependent application, from 6G communication systems to autonomous driving platforms, a large portion of computing should be near to the client side. Edge computing (AI at Edge) in mobile devices is one…

Convolutional Neural Networks (CNNs) have revolutionized the research in computer vision, due to their ability to capture complex patterns, resulting in high inference accuracies. However, the increasingly complex nature of these neural…

We present a new convolution layer for deep learning architectures which we call QuadConv -- an approximation to continuous convolution via quadrature. Our operator is developed explicitly for use on non-uniform, mesh-based data, and…

In object detection, reducing computational cost is as important as improving accuracy for most practical usages. This paper proposes a novel network structure, which is an order of magnitude lighter than other state-of-the-art networks…

Current state-of-the-art reading comprehension models rely heavily on recurrent neural networks. We explored an entirely different approach to question answering: a convolutional model. By their nature, these convolutional models are fast…

We tackle the problem of automatic portrait matting on mobile devices. The proposed model is aimed at attaining real-time inference on mobile devices with minimal degradation of model performance. Our model MMNet, based on multi-branch…

Recently, vision transformers started to show impressive results which outperform large convolution based models significantly. However, in the area of small models for mobile or resource constrained devices, ConvNet still has its own…

Although convolutional networks (ConvNets) have enjoyed great success in computer vision (CV), it suffers from capturing global information crucial to dense prediction tasks such as object detection and segmentation. In this work, we…

Video interpolation aims to generate a non-existent intermediate frame given the past and future frames. Many state-of-the-art methods achieve promising results by estimating the optical flow between the known frames and then generating the…

Recently deep convolutional neural networks have achieved significant success in salient object detection. However, existing state-of-the-art methods require high-end GPUs to achieve real-time performance, which makes them hard to adapt to…

Hardware accelerators for convolution neural networks (CNNs) enable real-time applications of artificial intelligence technology. However, most of the existing designs suffer from low hardware utilization or high area cost due to complex…

Complicated and deep neural network models can achieve high accuracy for image recognition. However, they require a huge amount of computations and model parameters, which are not suitable for mobile and embedded devices. Therefore,…

Aiming to obtain a high-resolution image, pansharpening involves the fusion of a multi-spectral image (MS) and a panchromatic image (PAN), the low-level vision task remaining significant and challenging in contemporary research. Most…

We propose a new convolution called Dynamic Region-Aware Convolution (DRConv), which can automatically assign multiple filters to corresponding spatial regions where features have similar representation. In this way, DRConv outperforms…

Deploying vision models across devices with varying resource constraints, or even on a single device where available compute fluctuates due to battery state, thermal throttling, or latency deadlines, typically requires training and…

We present MovePose, an optimized lightweight convolutional neural network designed specifically for real-time body pose estimation on CPU-based mobile devices. The current solutions do not provide satisfactory accuracy and speed for human…