相关论文: PSDNet and DPDNet: Efficient channel expansion, De…

With joint learning of sampling and recovery, the deep learning-based compressive sensing (DCS) has shown significant improvement in performance and running time reduction. Its reconstructed image, however, losses high-frequency content…

Depth is a vital piece of information for autonomous vehicles to perceive obstacles. Due to the relatively low price and small size of monocular cameras, depth estimation from a single RGB image has attracted great interest in the research…

Deep Convolutional Neural Networks (CNNs) have been widely used in various domains due to their impressive capabilities. These models are typically composed of a large number of 2D convolutional (Conv2D) layers with numerous trainable…

Deep convolutional neural networks, assisted by architectural design strategies, make extensive use of data augmentation techniques and layers with a high number of feature maps to embed object transformations. That is highly inefficient…

Deep neural networks often work well when they are over-parameterized and trained with a massive amount of noise and regularization, such as weight decay and dropout. Although dropout is widely used as a regularization technique for fully…

Unlike images which are represented in regular dense grids, 3D point clouds are irregular and unordered, hence applying convolution on them can be difficult. In this paper, we extend the dynamic filter to a new convolution operation, named…

This study presents a lightweight dual-domain super-resolution network (DDSRNet) that combines Spatial-Net with the discrete wavelet transform (DWT). Specifically, our proposed model comprises three main components: (1) a shallow feature…

The architecture of deep convolutional networks (CNNs) has evolved for years, becoming more accurate and faster. However, it is still challenging to design reasonable network structures that aim at obtaining the best accuracy under a…

We propose a hybrid reconstruction framework for dual-spectral CT (DSCT) that integrates iterative methods with deep learning models. The reconstruction process consists of two complementary components: a knowledge-driven module and a…

As designing appropriate Convolutional Neural Network (CNN) architecture in the context of a given application usually involves heavy human works or numerous GPU hours, the research community is soliciting the architecture-neutral CNN…

Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performances in applications such as image classification and language modeling. However, these techniques typically ignore device-related objectives…

Spiking neural networks (SNNs) have closer dynamics to the brain than current deep neural networks. Their low power consumption and sample efficiency make these networks interesting. Recently, several deep convolutional spiking neural…

Very deep convolutional neural networks offer excellent recognition results, yet their computational expense limits their impact for many real-world applications. We introduce BlockDrop, an approach that learns to dynamically choose which…

Multi-scale learning frameworks have been regarded as a capable class of models to boost semantic segmentation. The problem nevertheless is not trivial especially for the real-world deployments, which often demand high efficiency in…

Lightweight design, as a key approach to mitigate disparity between computational requirements of deep learning models and hardware performance, plays a pivotal role in advancing application of deep learning technologies on mobile and…

Deep convolutional neural networks (CNNs) for image denoising have recently attracted increasing research interest. However, plain networks cannot recover fine details for a complex task, such as real noisy images. In this paper, we…

Various architectures (such as GoogLeNets, ResNets, and DenseNets) have been proposed. However, the existing networks usually suffer from either redundancy of convolutional layers or insufficient utilization of parameters. To handle these…

To promote the generalization ability of breast tumor segmentation models, as well as to improve the segmentation performance for breast tumors with smaller size, low-contrast and irregular shape, we propose a progressive dual priori…

We propose combining memory saving techniques with traditional U-Net architectures to increase the complexity of the models on the Brain Tumor Segmentation (BraTS) challenge. The BraTS challenge consists of a 3D segmentation of a…

This paper presents how we can achieve the state-of-the-art accuracy in multi-category object detection task while minimizing the computational cost by adapting and combining recent technical innovations. Following the common pipeline of…