Related papers: Fast and High-Quality Image Denoising via Malleabl…
Deep convolutional neural networks achieve remarkable visual recognition performance, at the cost of high computational complexity. In this paper, we have a new design of efficient convolutional layers based on three schemes. The 3D…
Convolutional neural networks (CNNs) have shown remarkable performance in various computer vision tasks in recent years. However, the increasing model size has raised challenges in adopting them in real-time applications as well as mobile…
While scale-invariant modeling has substantially boosted the performance of visual recognition tasks, it remains largely under-explored in deep networks based image restoration. Naively applying those scale-invariant techniques (e.g.…
Convolutional Neural Networks (CNNs) are known for requiring extensive computational resources, and quantization is among the best and most common methods for compressing them. While aggressive quantization (i.e., less than 4-bits) performs…
Existing ultrasound deconvolution approaches unrealistically assume, primarily for computational reasons, that the convolution model relies on a spatially invariant kernel and circulant boundary conditions. We discard both restrictions and…
We introduce a new generator architecture, aimed at fast and efficient high-resolution image-to-image translation. We design the generator to be an extremely lightweight function of the full-resolution image. In fact, we use pixel-wise…
Convolutional Neural Networks (CNNs) have achieved great success due to the powerful feature learning ability of convolution layers. Specifically, the standard convolution traverses the input images/features using a sliding window scheme to…
Dynamic convolution learns a linear mixture of $n$ static kernels weighted with their sample-dependent attentions, demonstrating superior performance compared to normal convolution. However, existing designs are parameter-inefficient: they…
Recently, convolutional neural networks (CNN) have demonstrated impressive performance in various computer vision tasks. However, high performance hardware is typically indispensable for the application of CNN models due to the high…
Dynamic convolution enhances model capacity by adaptively combining multiple kernels, yet faces critical trade-offs: prior works either (1) incur significant parameter overhead by scaling kernel numbers linearly, (2) compromise inference…
While convolutional neural networks (CNNs) and vision transformers (ViTs) have advanced medical image segmentation, they face inherent limitations such as local receptive fields in CNNs and high computational complexity in ViTs. This paper…
Rapid developments in machine vision have led to advances in a variety of industries, from medical image analysis to autonomous systems. These achievements, however, typically necessitate digital neural networks with heavy computational…
Recently, deep-learning-based super-resolution methods have achieved excellent performances, but mainly focus on training a single generalized deep network by feeding numerous samples. Yet intuitively, each image has its representation, and…
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…
Convolution kernels are the basic structural component of convolutional neural networks (CNNs). In the last years there has been a growing interest in fisheye cameras for many applications. However, the radially symmetric projection model…
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…
Conventional deep convolutional neural networks (CNNs) apply convolution operators uniformly in space across all feature maps for hundreds of layers - this incurs a high computational cost for real-time applications. For many problems such…
The high demand for computational and storage resources severely impede the deployment of deep convolutional neural networks (CNNs) in limited-resource devices. Recent CNN architectures have proposed reduced complexity versions (e.g.…
The paper introduces the weighted convolution, a novel approach to the convolution for signals defined on regular grids (e.g., 2D images) through the application of an optimal density function to scale the contribution of neighbouring…
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…