Related papers: Res2Net: A New Multi-scale Backbone Architecture

Multispectral pan-sharpening aims at producing a high resolution (HR) multispectral (MS) image in both spatial and spectral domains by fusing a panchromatic (PAN) image and a corresponding MS image. In this paper, we propose a novel…

Most existing Convolutional Neural Networks(CNNs) used for action recognition are either difficult to optimize or underuse crucial temporal information. Inspired by the fact that the recurrent model consistently makes breakthroughs in the…

Convolutional neural network has recently achieved great success for image restoration (IR) and also offered hierarchical features. However, most deep CNN based IR models do not make full use of the hierarchical features from the original…

Recently, dense connections have attracted substantial attention in computer vision because they facilitate gradient flow and implicit deep supervision during training. Particularly, DenseNet, which connects each layer to every other layer…

In this work, we present a simple, highly efficient and modularized Dual Path Network (DPN) for image classification which presents a new topology of connection paths internally. By revealing the equivalence of the state-of-the-art Residual…

Convolutional neural networks have recently shown excellent results in general object detection and many other tasks. Albeit very effective, they involve many user-defined design choices. In this paper we want to better understand these…

A major bottleneck of pedestrian detection lies on the sharp performance deterioration in the presence of small-size pedestrians that are relatively far from the camera. Motivated by the observation that pedestrians of disparate spatial…

Recently, very deep convolutional neural networks (CNNs) have been attracting considerable attention in image restoration. However, as the depth grows, the long-term dependency problem is rarely realized for these very deep models, which…

Despite the rapid progress of neuromorphic computing, inadequate capacity and insufficient representation power of spiking neural networks (SNNs) severely restrict their application scope in practice. Residual learning and shortcuts have…

Capturing feature information effectively is of great importance in the field of computer vision. With the development of convolutional neural networks (CNNs), concepts like residual connection and multiple scales promote continual…

Accurate face detection and facial landmark localization are crucial to any face recognition system. We present a series of three single-stage RCNNs with different sized backbones (MobileNetV2-25, MobileNetV2-100, and ResNet101) and a…

Recent research has focused on using convolutional neural networks (CNNs) as the backbones in two-view correspondence learning, demonstrating significant superiority over methods based on multilayer perceptrons. However, CNN backbones that…

Capsule Networks (CapsNets) is a machine learning architecture proposed to overcome some of the shortcomings of convolutional neural networks (CNNs). However, CapsNets have mainly outperformed CNNs in datasets where images are small and/or…

Convolutional Neural Networks (CNNs) have been consistently proved state-of-the-art results in image Super-Resolution (SR), representing an exceptional opportunity for the remote sensing field to extract further information and knowledge…

This paper presents a comparative study of a custom convolutional neural network (CNN) architecture against widely used pretrained and transfer learning CNN models across five real-world image datasets. The datasets span binary…

Two-stream Convolutional Networks (ConvNets) have shown strong performance for human action recognition in videos. Recently, Residual Networks (ResNets) have arisen as a new technique to train extremely deep architectures. In this paper, we…

Deep CNN-based methods have so far achieved the state of the art results in multi-view 3D object reconstruction. Despite the considerable progress, the two core modules of these methods - multi-view feature extraction and fusion, are…

Large pretrained models are increasingly crucial in modern computer vision tasks. These models are typically used in downstream tasks by end-to-end finetuning, which is highly memory-intensive for tasks with high-resolution data, e.g.,…

In this work, we propose Retentive Network (RetNet) as a foundation architecture for large language models, simultaneously achieving training parallelism, low-cost inference, and good performance. We theoretically derive the connection…

Convolutional neural networks are the most successful models in single image super-resolution. Deeper networks, residual connections, and attention mechanisms have further improved their performance. However, these strategies often improve…