Related papers: Hybrid Composition with IdleBlock: More Efficient …

Recent work has shown that fast, compact low-bitwidth neural networks can be surprisingly accurate. These networks use homogeneous binarization: all parameters in each layer or (more commonly) the whole model have the same low bitwidth…

We introduce H3DNet, which takes a colorless 3D point cloud as input and outputs a collection of oriented object bounding boxes (or BB) and their semantic labels. The critical idea of H3DNet is to predict a hybrid set of geometric…

Although deep models have greatly improved the accuracy and robustness of image segmentation, obtaining segmentation results with highly accurate boundaries and fine structures is still a challenging problem. In this paper, we propose a…

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…

3D segmentation with deep learning if trained with full resolution is the ideal way of achieving the best accuracy. Unlike in 2D, 3D segmentation generally does not have sparse outliers, prevents leakage to surrounding soft tissues, at the…

We derive a relationship between network representation in energy-efficient neuromorphic architectures and block Toplitz convolutional matrices. Inspired by this connection, we develop deep convolutional networks using a family of…

Building footprint extraction from high-resolution aerial images is always an essential part of urban dynamic monitoring, planning and management. It has also been a challenging task in remote sensing research. In recent years, deep neural…

In this paper, we aim to reduce the computational cost of spatio-temporal deep neural networks, making them run as fast as their 2D counterparts while preserving state-of-the-art accuracy on video recognition benchmarks. To this end, we…

Recently deep learning-based methods have been applied in image compression and achieved many promising results. In this paper, we propose an improved hybrid layered image compression framework by combining deep learning and the traditional…

Automatic image segmentation technology is critical to the visual analysis. The autoencoder architecture has satisfying performance in various image segmentation tasks. However, autoencoders based on convolutional neural networks (CNN) seem…

Recent advancements in deep neural networks have driven significant progress in image enhancement (IE). However, deploying deep learning models on resource-constrained platforms, such as mobile devices, remains challenging due to high…

We propose a deep convolutional neural network architecture codenamed "Inception", which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014…

Deep learning algorithms, especially Transformer-based models, have achieved significant performance by capturing long-range dependencies and historical information. However, the power of convolution has not been fully investigated.…

Approaches to machine intelligence based on brain models have stressed the use of neural networks for generalization. Here we propose the use of a hybrid neural network architecture that uses two kind of neural networks simultaneously: (i)…

MobileViT (MobileViTv1) combines convolutional neural networks (CNNs) and vision transformers (ViTs) to create light-weight models for mobile vision tasks. Though the main MobileViTv1-block helps to achieve competitive state-of-the-art…

Convolution operator is the core of convolutional neural networks (CNNs) and occupies the most computation cost. To make CNNs more efficient, many methods have been proposed to either design lightweight networks or compress models. Although…

Major winning Convolutional Neural Networks (CNNs), such as AlexNet, VGGNet, ResNet, GoogleNet, include tens to hundreds of millions of parameters, which impose considerable computation and memory overhead. This limits their practical use…

Despite the good results that have been achieved in unimodal segmentation, the inherent limitations of individual data increase the difficulty of achieving breakthroughs in performance. For that reason, multi-modal learning is increasingly…

Magnetic resonance imaging (MRI) is a widely used neuroimaging technique that can provide images of different contrasts (i.e., modalities). Fusing this multi-modal data has proven particularly effective for boosting model performance in…

The Capsule Network is widely believed to be more robust than Convolutional Networks. However, there are no comprehensive comparisons between these two networks, and it is also unknown which components in the CapsNet affect its robustness.…