相关论文: DAC: Data-free Automatic Acceleration of Convoluti…

Scale-sensitive object detection remains a challenging task, where most of the existing methods could not learn it explicitly and are not robust to scale variance. In addition, the most existing methods are less efficient during training or…

In image denoising networks, feature scaling is widely used to enlarge the receptive field size and reduce computational costs. This practice, however, also leads to the loss of high-frequency information and fails to consider within-scale…

Convolutional neural networks excel in a number of computer vision tasks. One of their most crucial architectural elements is the effective receptive field size, that has to be manually set to accommodate a specific task. Standard solutions…

Deep convolutional neural network (CNN) inference requires significant amount of memory and computation, which limits its deployment on embedded devices. To alleviate these problems to some extent, prior research utilize low precision…

We develop a novel deep contour detection algorithm with a top-down fully convolutional encoder-decoder network. Our proposed method, named TD-CEDN, solves two important issues in this low-level vision problem: (1) learning multi-scale and…

CNN architectures are generally heavy on memory and computational requirements which makes them infeasible for embedded systems with limited hardware resources. We propose dual convolutional kernels (DualConv) for constructing lightweight…

Early fault diagnosis in complex mechanical systems such as gearbox has always been a great challenge, even with the recent development in deep neural networks. The performance of a classic fault diagnosis system predominantly depends on…

Despite the remarkable performance, modern deep neural networks are inevitably accompanied by a significant amount of computational cost for learning and deployment, which may be incompatible with their usage on edge devices. Recent efforts…

We present a new deep supervised learning method for intrinsic decomposition of a single image into its albedo and shading components. Our contributions are based on a new fully convolutional neural network that estimates absolute albedo…

Deep neural networks (DNNs) can be made hardware-efficient by reducing the numerical precision of the weights and activations of the network and by improving the network's resilience to noise. However, this gain in efficiency often comes at…

With the benefit of deep learning techniques, recent researches have made significant progress in image compression artifacts reduction. Despite their improved performances, prevailing methods only focus on learning a mapping from the…

Collaborative intelligence is a new paradigm for efficient deployment of deep neural networks across the mobile-cloud infrastructure. By dividing the network between the mobile and the cloud, it is possible to distribute the computational…

Object detection aims at high speed and accuracy simultaneously. However, fast models are usually less accurate, while accurate models cannot satisfy our need for speed. A fast model can be 10 times faster but 50\% less accurate than an…

Depthwise separable convolution (DSC) has emerged as a crucial technique, especially for resource-constrained devices. In this paper, we propose a dual-engine for the DSC hardware accelerator, which enables the full utilization of depthwise…

The accuracy of deep convolutional neural networks (CNNs) generally improves when fueled with high resolution images. However, this often comes at a high computational cost and high memory footprint. Inspired by the fact that not all…

Inspection of insulators is important to ensure reliable operation of the power system. Deep learning is being increasingly exploited to automate the inspection process by leveraging object detection models to analyse aerial images captured…

Dilated convolution, which expands the receptive field by inserting gaps between its consecutive elements, is widely employed in computer vision. In this study, we propose three strategies to improve individual phases of dilated convolution…

Distributed Acoustic Sensing (DAS) is a promising technology introducing a new paradigm in the acquisition of high-resolution seismic data. However, DAS data often show weak signals compared to the background noise, especially in tough…

Deconvolution, imaging and calibration of data from radio interferometers is a challenging computational (inverse) problem. The upcoming generation of radio telescopes poses significant challenges to existing, and well proven data reduction…

Task-agnostic prompt compression leverages the redundancy in natural language to reduce computational overhead and enhance information density within prompts, especially in long-context scenarios. Existing methods predominantly rely on…