To construct small mobile networks without performance loss and address the over-fitting issues caused by the less abundant training datasets, this paper proposes a novel super sparse convolutional (SSC) kernel, and its corresponding network is called SSC-Net. In a SSC kernel, every spatial kernel...
Traditional convolutional neural network (CNN) methods rely on dense tensors, which makes them suboptimal for spatially sparse data. In this paper, we propose a CNN model based on sparse tensors for efficient processing of high-resolution shapes represented as binary voxel occupancy grids. In contr...
Image super-resolution using deep convolutional networks(SRCNN) 2、VGGNet采用连续的几个3×3的卷积核代替AlexNet中的较大卷积核,在保证感受野的情况下提升了网络的深度。与之对应,图像超分辨率网络也开始使用更小的卷积核和使用更多的映射层。 代表论文: Accelerating the super-resolution convolutional neural networ...
In addition, in order to improve the efficiency of the serial remote sensing image superresolution algorithm based on the intermediate layer convolutional neural network, the dictionary learning superresolution algorithm based on sparse representation is used for reference, and the convolutional neural ...
Recently, convolutional neural networks (CNNs), with their powerful learning ability, have shown great performance in many challenging computer vision applications, including, for example, object recognition (Girshick et al., 2014) and image classification (He et al., 2016). Inspired by significant...
The mapping is represented as a deep convolutional neural network (CNN) that takes the low-resolution image as the input and outputs the high-resolution one. We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network. But unlike traditional...
3 CONVOLUTIONAL NEURAL NETWORKS FORSUPER-RESOLUTION 3.1 Formulation 3.1.1 Patch extraction and representation 3.1.2 Non-linear mapping 3.1.3 Reconstruction 3.2 Relationship to Sparse-Coding-Based Methods 3.3 Training 4 EXPERIMENTS 4.1 Training Data ...
particularly convolutional neural networks (CNNs) and generative adversarial networks (GANs), have gained prominence in the field of super-resolution due to their impressive performance and ability to learn hierarchical features. These newer techniques often outperform traditional sparse-coding-based methods...
As a successful deep model applied in image super-resolution (SR), the Super-Resolution Convolutional Neural Network (SRCNN) [1, 2] has demonstrated superior performance to the previous hand-crafted models either in speed and restoration quality. However
Hyperspectral Image Super-Resolution via Non-Local Sparse Tensor Factorization Renwei Dian, Leyuan Fang, Shutao Li [ pdf ] [ poster ] Simultaneous Super-Resolution and Cross-Modality Synthesis of 3D Medical Images Using Weakly-Supervised Joint Convolutional Sparse Coding Yawen Huang, Ling Shao, ...