Related papers: A 7K Parameter Model for Underwater Image Enhancem…

Underwater visual perception is essentially important for underwater exploration, archeology, ecosystem and so on. The low illumination, light reflections, scattering, absorption and suspended particles inevitably lead to the critically…

Deep Learning (DL) algorithms are emerging as a key alternative to computationally expensive CFD simulations. However, state-of-the-art DL approaches require large and high-resolution training data to learn accurate models. The size and…

Recently, deep convolutional neural network methods have achieved an excellent performance in image superresolution (SR), but they can not be easily applied to embedded devices due to large memory cost. To solve this problem, we propose a…

On-site estimation of sea state parameters is crucial for ship navigation systems' accuracy, stability, and efficiency. Extensive research has been conducted on model-based estimating methods utilizing only ship motion responses. Model-free…

While current state-of-the-art NMT models, such as RNN seq2seq and Transformers, possess a large number of parameters, they are still shallow in comparison to convolutional models used for both text and vision applications. In this work we…

Majority of deep learning methods utilize vanilla convolution for enhancing underwater images. While vanilla convolution excels in capturing local features and learning the spatial hierarchical structure of images, it tends to smooth input…

In the recent years impressive advances were made for single image super-resolution. Deep learning is behind a big part of this success. Deep(er) architecture design and external priors modeling are the key ingredients. The internal…

Hyperspectral image (HSI) classification faces critical challenges, including high spectral dimensionality, complex spectral-spatial correlations, and limited training samples with severe class imbalance. While CNNs excel at local feature…

Attention mechanisms, particularly channel attention, have become highly influential in numerous computer vision tasks. Despite their effectiveness, many existing methods primarily focus on optimizing performance through complex attention…

Deep neural networks have demonstrated state-of-the-art performance for feature-based image matching through the advent of new large and diverse datasets. However, there has been little work on evaluating the computational cost, model size,…

In recent years, channel attention mechanism has been widely investigated due to its great potential in improving the performance of deep convolutional neural networks (CNNs) in many vision tasks. However, in most of the existing methods,…

We propose a scalable framework for the learning of high-dimensional parametric maps via adaptively constructed residual network (ResNet) maps between reduced bases of the inputs and outputs. When just few training data are available, it is…

Although large-scale labeled data are essential for deep convolutional neural networks (ConvNets) to learn high-level semantic visual representations, it is time-consuming and impractical to collect and annotate large-scale datasets. A…

In order to address the issue that medical image would suffer from severe blurring caused by the lack of high-frequency details in the process of image super-resolution reconstruction, a novel medical image super-resolution method based on…

Recent advances in deep learning, particularly neural networks, have significantly impacted a wide range of fields, including the automatic enhancement of underwater images. This paper presents a deep learning-based approach to improving…

Low-light images suffer from severe noise and low illumination. Current deep learning models that are trained with real-world images have excellent noise reduction, but a ratio parameter must be chosen manually to complete the enhancement…

Low-light image enhancement is challenging in that it needs to consider not only brightness recovery but also complex issues like color distortion and noise, which usually hide in the dark. Simply adjusting the brightness of a low-light…

Single-image super-resolution (SISR) has achieved significant breakthroughs with the development of deep learning. However, these methods are difficult to be applied in real-world scenarios since they are inevitably accompanied by the…

Despite the recent progress in image dehazing, several problems remain largely unsolved such as robustness for varying scenes, the visual quality of reconstructed images, and effectiveness and flexibility for applications. To tackle these…

FlowNet2, the state-of-the-art convolutional neural network (CNN) for optical flow estimation, requires over 160M parameters to achieve accurate flow estimation. In this paper we present an alternative network that outperforms FlowNet2 on…