Captured images of outdoor scenes usually exhibit low visibility in cases of severe haze, which interferes with optical imaging and degrades image quality. Most of the existing methods solve the single-image dehazing problem by applying supervised training on paired images; however, in practice, the pairing of real-world images is not viable. Additionally, the processing speed of individual dehazing models is important in practical applications. In this study, a novel unsupervised single image dehazing network (USID-Net) based on disentangled representations without paired training images is explored. Furthermore, considering the trade-off between performance and memory storage, a compact multi-scale feature attention (MFA) module is developed, integrating multi-scale feature representation and attention mechanism to facilitate feature representation. To effectively extract haze information, a mechanism referred to as OctEncoder is designed to include multi-frequency representations that can capture more global information. Extensive experiments show that USID-Net achieves competitive dehazing results and a relatively high processing speed compared to state-of-the-art methods.

Captured outdoor scene images are easily affected by haze. Most image dehazing methods have limited generalization capabilities for real-world hazy images owing to the complexities of real-world environments and domain gaps in the training datasets. This paper proposes a semi-supervised single-image dehazing network based on disentangled meta-knowledge. The symmetric and heterogeneous design of the disentangled network is conducive to the separation of the content and mask features of hazy images and these features are used as meta-knowledge to guide feature fusion in the dehazing network. Moreover, functions describing constant-color and disentangled-reconstruction-checking losses are designed to ensure the subjective qualities of the generated dehazed images. The results of extensive experiments conducted on synthetic datasets and real-world images indicate that the proposed algorithm outperforms state-of-the-art single-image dehazing algorithms. In addition, the algorithm effectively improves the performance of object-detection tasks. The source code is publicly available at https://github.com/dehazing/DNDM .

Hyperspectral images are one of the most important fundamental and strategic information resources, imaging the same ground object with hundreds of spectral bands varying from the ultraviolet to the microwave. With the emergence of huge volumes of high-resolution hyperspectral images produced by all sorts of imaging sensors, processing and analysis of these images requires effective retrieval techniques. How to ensure retrieval accuracy and efficiency is a challenging task in the field of hyperspectral image retrieval. In this paper, an efficient hyperspectral image retrieval method is proposed. In principle, our method includes the following steps: (1) in order to make powerful representations for hyperspectral images, deep spectral-spatial features are extracted with the Deep Convolutional Generative Adversarial Networks (DCGAN) model; (2) considering the higher dimensionality of deep spectral-spatial features, t-Distributed Stochastic Neighbor Embedding-based Nonlinear Manifold (t-SNE-based NM) hashing is utilized to make dimensionality reduction by learning compact binary codes embedded on the intrinsic manifolds of deep spectral-spatial features for balancing between learning efficiency and retrieval accuracy; and (3) multi-index hashing in Hamming space is measured to find similar hyperspectral images. Five comparative experiments are conducted to verify the effectiveness of deep spectral-spatial features, dimensionality reduction of t-SNE-based NM hashing, and similarity measurement of multi-index hashing. The experimental results using NASA datasets show that our hyperspectral image retrieval method can achieve comparable and superior performance with less computational time.

Haze seriously affects the reliability of industrial systems, especially vision-based outdoor industrial systems such as autopilot systems. A majority of existing dehazing methods are not specifically designed for industrial systems and do not consider the reliability and resource cost of industrial system implementation. In this article, a novel meta-attention dehazing network (MADN) is proposed for direct restoration of clear images from hazy images without using the physical scattering model. Combined with parallel operation and enhancement modules, the meta-network automatically selects the most suitable dehazing network structure based on the current input hazy image by a meta-attention module. In addition, a novel feature loss calculated by the meta-network is proposed, which can accelerate the convergence of the dehazing network to meet the application requirements of practical industrial systems. A large number of experimental results on synthetic and real-world datasets show that the proposed MADN satisfies the needs of industrial systems.

In recent years, Transformer-based Change Detection (CD) in Remote Sensing Images has achieved significant advances, making it an emerging hot research topic. However, the current CD methods suffer from some problems, such as incomplete detection of change regions and missed detection of small change regions. In this paper, a Global Context-aware Transformer is proposed for CD tasks, named GCFormer, to address above issues by efficiently enhancing the global context information. It is fulfilled from two aspects based on the hybrid Convolutional Neural Network (CNN)+Transformer framework. Firstly, a Multi-Receptive Field Conv-Attention (MRFCA) mechanism is designed, which combines dilated convolutions with multiple rates and Conv-Attention, fully leveraging the advantages of convolution operation and self-attention mechanism. It is embedded at the highest layer of CNN to extract multi-receptive-field global context information. Secondly, a Context-aware Relative Position Encoding (CRPE) mode is proposed to replace the Absolute Position Encoding (APE) mode of Transformer. As a result, it can capture long-range dependency more efficiently and further enhance the global context information extraction and representation ability of the network. Experimental results on three public benchmark datasets of LEVIR-CD, WHU-CD and DSIFN-CD show that, the proposed GCFormer achieves superior detection performance with lower model complexity than the state-of-the-art Transformer-based CD methods. The source code is available at: https://github.com/yuwanting828/yuwanting828.github.io.