Related papers: Concatenated Attention Neural Network for Image Re…

Deep Convolutional Neural Networks (CNNs) for image classification successively alternate convolutions and downsampling operations, such as pooling layers or strided convolutions, resulting in lower resolution features the deeper the…

Attention mechanism of late has been quite popular in the computer vision community. A lot of work has been done to improve the performance of the network, although almost always it results in increased computational complexity. In this…

In photoacoustic tomography (PAT), the acoustic pressure waves produced by optical excitation are measured by an array of detectors and used to reconstruct an image. Sparse spatial sampling and limited-view detection are two common…

In this paper, we propose a general dual convolutional neural network (DualCNN) for low-level vision problems, e.g., super-resolution, edge-preserving filtering, deraining and dehazing. These problems usually involve the estimation of two…

Image decomposition aims to analyze an image into elementary components, which is essential for numerous downstream tasks and also by nature provides certain interpretability to the analysis. Deep learning can be powerful for such tasks,…

Attention-based learning for fine-grained image recognition remains a challenging task, where most of the existing methods treat each object part in isolation, while neglecting the correlations among them. In addition, the multi-stage or…

Feature reassembly, i.e. feature downsampling and upsampling, is a key operation in a number of modern convolutional network architectures, e.g., residual networks and feature pyramids. Its design is critical for dense prediction tasks such…

Compressive sensing (CS), aiming to reconstruct an image/signal from a small set of random measurements has attracted considerable attentions in recent years. Due to the high dimensionality of images, previous CS methods mainly work on…

One popular strategy for image denoising is to design a generalized regularization term that is capable of exploring the implicit prior underlying data observation. Convolutional neural networks (CNN) have shown the powerful capability to…

The inception network has been shown to provide good performance on image classification problems, but there are not much evidences that it is also effective for the image restoration or pixel-wise labeling problems. For image restoration…

Images captured under outdoor scenes usually suffer from low contrast and limited visibility due to suspended atmospheric particles, which directly affects the quality of photos. Despite numerous image dehazing methods have been proposed,…

Photoacoustic (PA) computed tomography (PACT) reconstructs the initial pressure distribution from raw PA signals. The standard reconstruction of medical image could cause the artifacts due to interferences or ill-posed setup. Recently, deep…

In this paper, we introduce robust and synergetic hand-crafted features and a simple but efficient deep feature from a convolutional neural network (CNN) architecture for defocus estimation. This paper systematically analyzes the…

This paper studies the computational offloading of CNN inference in device-edge co-inference systems. Inspired by the emerging paradigm semantic communication, we propose a novel autoencoder-based CNN architecture (AECNN), for effective…

Recently, convolutional neural networks (CNNs) have been used as a powerful tool to solve many problems of machine learning and computer vision. In this paper, we aim to provide insight on the property of convolutional neural networks, as…

Undersampling the k-space data is widely adopted for acceleration of Magnetic Resonance Imaging (MRI). Current deep learning based approaches for supervised learning of MRI image reconstruction employ real-valued operations and…

Image denoising and high-level vision tasks are usually handled independently in the conventional practice of computer vision, and their connection is fragile. In this paper, we cope with the two jointly and explore the mutual influence…

Image denoising is an important low-level computer vision task, which aims to reconstruct a noise-free and high-quality image from a noisy image. With the development of deep learning, convolutional neural network (CNN) has been gradually…

In this paper we propose a generative adversarial network (GAN) framework to enhance the perceptual quality of compressed videos. Our framework includes attention and adaptation to different quantization parameters (QPs) in a single model.…

The sensitivity of deep neural networks to compressed images hinders their usage in many real applications, which means classification networks may fail just after taking a screenshot and saving it as a compressed file. In this paper, we…