Article
Computer Science, Software Engineering
Yue Yang, Yong Qi, Saiyu Qi
Summary: In this paper, a relation-consistency graph convolutional network (RGCN) is proposed for high-quality image rendering. By introducing the spatial graph attention (SGA) and spatial pyramid pooling mechanism, it can better model the relationships between image features, enhance the feature representation, and maintain the invariant of global relationships through a relation-consistency loss, thereby achieving more realistic image reconstruction.
Article
Environmental Sciences
Ziqian Liu, Wenbing Wang, Qing Ma, Xianming Liu, Junjun Jiang
Summary: In this paper, a full 3D convolutional neural network (F3DUN) is proposed for hyperspectral image super-resolution (HSISR) tasks. The F3DUN model combined with the U-Net architecture achieves state-of-the-art performance on HSISR tasks by utilizing skip connections and multi-scale features. Additionally, the paper compares F3DUN with a 3D/2D mixed model and finds that the full 3D CNN has a larger capacity and can obtain better results with the same number of parameters. Furthermore, experimental results demonstrate that the full 3D CNN model is less sensitive to data scaling and outperforms the 3D/2D mixed model on small-scale datasets.
Article
Geochemistry & Geophysics
Sen Jia, Shuangzhao Zhu, Zhihao Wang, Meng Xu, Weixi Wang, Yujuan Guo
Summary: With the rapid development of deep convolutional neural networks, super-resolution in hyperspectral images has made significant progress. However, current methods lack effective ways to extract spectral information and suffer from parameter redundancy and model complexity. In this study, we propose a diffused CNN approach that adds spectral convolutions into the enhanced convolutional neural block to better characterize spectral features and improve reconstruction efficiency through feature fusion and image enhancement.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Computer Science, Artificial Intelligence
Saeed Anwar, Nick Barnes
Summary: The research proposes a compact and accurate super-resolution algorithm DRLN, which achieves deep supervision learning through cascading residual structures and densely concatenated residual block settings, and models inter-level and intra-level dependencies between crucial features using Laplacian attention. Comprehensive evaluations on various test datasets show that the DRLN algorithm performs significantly better in terms of visual quality and accuracy compared to other methods.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Information Systems
Dongyang Zhang, Jie Shao, Zhenwen Liang, Lianli Gao, Heng Tao Shen
Summary: This study introduces a cascaded super-resolution convolutional neural network (CSRCNN) to address the aliasing artifacts and high computational costs caused by existing methods that use interpolation during the beginning stage. Experimental results show that the proposed network achieves superior performance, especially with an 8x upsampling factor.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Environmental Sciences
Xiuchao Yue, Xiaoxuan Chen, Wanxu Zhang, Hang Ma, Lin Wang, Jiayang Zhang, Mengwei Wang, Bo Jiang
Summary: A novel super-resolution method is proposed to reconstruct high-resolution remote sensing images, which outperforms state-of-the-art approaches in both quantitative indicators and visual qualities. The method utilizes preclassification, different SR networks, edge extraction, and loss functions to enhance the image reconstruction process.
Article
Geochemistry & Geophysics
Shi Chen, Lefei Zhang, Liangpei Zhang
Summary: The proposed MSDformer method utilizes CNN for local spatial-spectral information and Transformer for global spatial-spectral information, achieving excellent SR performance and outperforming state-of-the-art methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Computer Science, Information Systems
Tiesong Zhao, Yuting Lin, Yiwen Xu, Weiling Chen, Zhou Wang
Summary: This study introduces a method for image super-resolution quality assessment using a large-scale database and deep learning models. A SISAR database was constructed with a novel semi-automatic labeling approach, and a DISQ model was used for quality prediction, demonstrating promising performance in cross-database tests. The SISAR database and DISQ model will be publicly available for reproducible research.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Computer Science, Artificial Intelligence
Kejie Lyu, Sicheng Pan, Yingming Li, Zhongfei Zhang
Summary: In this paper, a new Joint Image Super-resolution and Enhancement Network (JSENet) is proposed, which is the first end-to-end method based on deep learning for joint SR and IE. JSENet seamlessly integrates the two tasks together using a bilateral learning framework, and two lightweight modules are designed for restoring details and generating color transformation coefficients respectively, improving the algorithm's deployability in real-world applications.
Article
Computer Science, Artificial Intelligence
Xiangyu Xu, Yongrui Ma, Wenxiu Sun, Ming-Hsuan Yang
Summary: This paper focuses on the problem of real-scene single image super-resolution and proposes a method to generate realistic training data by mimicking the imaging process of digital cameras. A two-branch convolutional neural network is developed to exploit the radiance information originally-recorded in raw images. Additionally, dense channel-attention blocks and a learning-based guided filter network are proposed for better image restoration and color correction.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Engineering, Electrical & Electronic
Kan Chang, Hengxin Li, Yufei Tan, Pak Lun Kevin Ding, Baoxin Li
Summary: This paper proposes an effective joint demosaicking and super-resolution method through a two-stage CNN architecture. Experimental results demonstrate the superiority of this method over other state-of-the-art demosaicking and super-resolution methods, with the added benefit of smaller model size.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Engineering, Aerospace
Yanshan LI, Li Zhou, Fan Xu, Shifu Chen
Summary: In this study, we propose an Optical-Guided Super-Resolution Network (OGSRN) for SAR image with large scale factors. OGSRN consists of a SAR image SuperResolution U-Net (SRUN) and a SAR-to-Optical Residual Translation Network (SORTN). Under the guidance of optical images, OGSRN achieves excellent performance in super-resolution of SAR images.
CHINESE JOURNAL OF AERONAUTICS
(2022)
Review
Computer Science, Information Systems
Li Yu, Yunpeng Ma, Song Hong, Ke Chen
Summary: This paper outlines the importance of light field super-resolution, highlights the characteristics and challenges of light field images, and compares and discusses traditional methods and deep-learning-based methods.
Article
Computer Science, Information Systems
Armin Mehri, Parichehr Behjati, Angel Domingo Sappa
Summary: Image Super Resolution is a potential approach to improve the image quality of low-resolution optical sensors. This paper presents a dual stream Transformer-based method that uses a low-cost channel (visible image) as a guide to enhance the image quality of an expensive channel (infrared image).
Article
Environmental Sciences
Zhenjie Tang, Qing Xu, Pengfei Wu, Zhenwei Shi, Bin Pan
Summary: The article introduces a novel convolutional neural network structure for hyperspectral image super-resolution, which utilizes a feedback structure and a local-global spectral block to extract spatial and spectral features, addressing the challenges posed by high-dimensional and complex spectral characteristics.
Article
Computer Science, Artificial Intelligence
Guang-Hai Liu, Zuo-Yong Li, Jing-Yu Yang, David Zhang
Summary: This article introduces a novel image retrieval method that improves retrieval performance by using sublimated deep features. The method incorporates orientation-selective features and color perceptual features, effectively mimicking these mechanisms to provide a more discriminating representation.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Fengguang Peng, Zihan Ding, Ziming Chen, Gang Wang, Tianrui Hui, Si Liu, Hang Shi
Summary: RGB-Thermal (RGB-T) semantic segmentation is an emerging task that aims to improve the robustness of segmentation methods under extreme imaging conditions by using thermal infrared modality. The challenges of foreground-background distinguishment and complementary information mining are addressed by proposing a cross modulation process with two collaborative components. Experimental results show that the proposed method achieves state-of-the-art performances on current RGB-T segmentation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Baihong Han, Xiaoyan Jiang, Zhijun Fang, Hamido Fujita, Yongbin Gao
Summary: This paper proposes a novel automatic prompt generation method called F-SCP, which focuses on generating accurate prompts for low-accuracy classes and similar classes. Experimental results show that our approach outperforms state-of-the-art methods on six multi-domain datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Huikai Liu, Ao Zhang, Wenqian Zhu, Bin Fu, Bingjian Ding, Shengwu Xiong
Summary: Adverse weather conditions present challenges for computer vision tasks, and image de-weathering is an important component of image restoration. This paper proposes a multi-patch skip-forward structure and a Residual Deformable Convolutional module to improve feature extraction and pixel-wise reconstruction.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Oliver M. Crook, Mihai Cucuringu, Tim Hurst, Carola-Bibiane Schonlieb, Matthew Thorpe, Konstantinos C. Zygalakis
Summary: The transportation LP distance (TLP) is a generalization of the Wasserstein WP distance that can be applied directly to color or multi-channelled images, as well as multivariate time-series. TLP interprets signals as functions, while WP interprets signals as measures. Although both distances are powerful tools in modeling data with spatial or temporal perturbations, their computational cost can be prohibitively high for moderate pattern recognition tasks. The linear Wasserstein distance offers a method for projecting signals into a Euclidean space, and in this study, we propose linear versions of the TLP distance (LTLP) that show significant improvement over the linear WP distance in signal processing tasks while being several orders of magnitude faster to compute than the TLP distance.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Haitao Tian, Shiru Qu, Pierre Payeur
Summary: This paper proposes a method of target-dependent classifier, which optimizes the joint hypothesis of domain adaptation into a target-dependent hypothesis that better fits with the target domain clusters through an unsupervised fine-tuning strategy and the concept of meta-learning. Experimental results demonstrate that this method outperforms existing techniques in synthetic-to-real adaptation and cross-city adaptation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Qingsen Yan, Axi Niu, Chaoqun Wang, Wei Dong, Marcin Wozniak, Yanning Zhang
Summary: Deep learning-based methods have achieved remarkable results in the field of super-resolution. However, the limitation of paired training image sets has led researchers to explore self-supervised learning. However, the assumption of inaccurate downscaling kernel functions often leads to degraded results. To address this issue, this paper introduces KGSR, a kernel-guided network that trains both upscaling and downscaling networks to generate high-quality high-resolution images even without knowing the actual downscaling process.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Yifan Chen, Xuelong Li
Summary: Gait recognition is a popular technology for identification due to its ability to capture gait features over long distances without cooperation. However, current methods face challenges as they use a single network to extract both temporal and spatial features. To solve this problem, we propose a two-branch network that focuses on spatial and temporal feature extraction separately. By combining these features, we can effectively learn the spatio-temporal information of gait sequences.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Wei Shi, Wentao Zhang, Wei-shi Zheng, Ruixuan Wang
Summary: This article proposes a simple yet effective visualization framework called PAMI, which does not require detailed model structure and parameters to obtain visualization results. It can be applied to various prediction tasks with different model backbones and input formats.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Xiaobo Hu, Jianbo Su, Jun Zhang
Summary: This paper reviews the latest technologies in pattern recognition, highlighting their instabilities and failures in practical applications. From a control perspective, the significance of disturbance rejection in pattern recognition is discussed, and the existing problems are summarized. Finally, potential solutions related to the application of compensation on features are discussed to emphasize future research directions.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Andres Felipe Posada-Moreno, Nikita Surya, Sebastian Trimpe
Summary: Convolutional neural networks are widely used in critical systems, and explainable artificial intelligence has proposed methods for generating high-level explanations. However, these methods lack the ability to determine the location of concepts. To address this, we propose a novel method for automatic concept extraction and localization based on pixel-wise aggregations, and validate it using synthetic datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Peng Bao, Jianian Li, Rong Yan, Zhongyi Liu
Summary: In this paper, a novel Dynamic Graph Contrastive Learning framework, DyGCL, is proposed to capture the temporal consistency in dynamic graphs and achieve good performance in node representation learning.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Kristian Schultz, Saptarshi Bej, Waldemar Hahn, Markus Wolfien, Prashant Srivastava, Olaf Wolkenhauer
Summary: Research indicates that deep generative models perform poorly compared to linear interpolation-based methods for synthetic data generation on small, imbalanced tabular datasets. To address this, a new approach called ConvGeN, combining convex space learning with deep generative models, has been proposed. ConvGeN improves imbalanced classification on small datasets while remaining competitive with existing linear interpolation methods.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Khondaker Tasrif Noor, Antonio Robles-Kelly
Summary: In this paper, the authors propose H-CapsNet, a capsule network designed for hierarchical image classification. The network effectively captures hierarchical relationships using dedicated capsules for each class hierarchy. A modified hinge loss is utilized to enforce consistency among the involved hierarchies. Additionally, a strategy for dynamically adjusting training parameters is presented to achieve better balance between the class hierarchies. Experimental results demonstrate that H-CapsNet outperforms competing hierarchical classification networks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Lei Liu, Guorun Li, Yuefeng Du, Xiaoyu Li, Xiuheng Wu, Zhi Qiao, Tianyi Wang
Summary: This study proposes a new agricultural image segmentation model called CS-Net, which uses Simple-Attention Block and Simpleformer to improve accuracy and inference speed, and addresses the issue of performance collapse of Transformers in agricultural image processing.
PATTERN RECOGNITION
(2024)