Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Honggang Chen et al.
Summary: This study proposes a self-supervised cycle-consistent learning-based scale-arbitrary super-resolution framework (SCL-SASR) for real-world images. The framework includes a Scale-Arbitrary Super-Resolution Network (SASRN) and an inverse Scale-Arbitrary Resolution-Degradation Network (SARDN), which ensure the adaptability to image-specific degradations and the ability to handle arbitrary scaling factors.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Yuting Wan et al.
Summary: Due to noise during data acquisition, the quality of hyperspectral images is degraded and their applications are limited. Traditional methods use low-rank and sparse matrix decomposition to restore pure data, but optimization of the l0-norm is difficult. This article proposes an accurate multiobjective low-rank and sparse denoising framework for accurate modeling without sensitive regularization parameters, achieving effective optimization through a subfitness strategy.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Jianwen Song et al.
Summary: This paper proposes a super-resolution phase retrieval network (SRPRNet) to address the issues of low accuracy and low resolution in single-pattern structured light 3D imaging. By introducing a phase-shifting module and a refinement and super-resolution module, multi-scale features can be extracted and refined and super-resolution phase components can be obtained, resulting in high-resolution absolute phase. Experimental results show that SRPRNet achieves state-of-the-art performance on 1x, 2x, and 4x super-resolution phase retrieval tasks.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Qian Ning et al.
Summary: This paper introduces a method that combines model-guided design (MoD) with neural architecture search (NAS) to address the optimization gap issue in image denoising. By constructing a new search space and developing more stable and efficient differential search strategies, the proposed method achieves comparable or even better PSNR performance than current state-of-the-art methods with fewer parameters, fewer flops, and less testing time.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Xinyi Wu et al.
Summary: In this paper, a novel domain adaptation network (DANIA) is proposed for nighttime semantic image segmentation. By leveraging a labeled daytime dataset and an unlabeled dataset containing coarsely aligned day-night image pairs, DANIA performs multi-target adaptation via adversarial training in the network. Pixel-level predictions on a daytime image are used as pseudo supervision to segment its counterpart nighttime image. Furthermore, image alignment and re-weighting strategy are applied to improve the predictions.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Bin Chen et al.
Summary: DPQNs have been successfully used in image retrieval due to their powerful feature extraction ability and high efficiency. However, little effort has been devoted to investigating how adversarial examples affect DPQNs, which may raise safety concerns in commercial search engines. Therefore, we propose an adversarial example generation framework to attack DPQN-based retrieval systems.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Jiaojiao Li et al.
Summary: A largely ignored fact in spectral super-resolution (SSR) is that the subsistent mapping methods neglect the auxiliary prior of camera spectral sensitivity (CSS) and only pay attention to wider or deeper network framework design while ignoring to excavate the spatial and spectral dependencies among intermediate layers, hence constraining representational capability of convolutional neural networks (CNNs). To conquer these drawbacks, we propose a novel deep hybrid 2-D-3-D CNN based on dual second-order attention with CSS prior (HSACS), which can excavate sufficient spatial-spectral context information. The experimental results demonstrate the superiority and progressiveness of the presented approach in terms of quantitative metrics and visual effect over SOTA SSR methods.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Information Systems
Hongyang Jiang et al.
Summary: This paper introduces a multi-learner based few-shot learning method for multiple medical image classification tasks, combining meta-learning, transfer-learning, and metric-learning. Through transfer-learning on base classes and meta-learning on new tasks, the metric-learner and task-learner can quickly adapt to unseen tasks. Real-time data augmentation and dynamic Gaussian disturbance soft label scheme are also used to improve learning efficiency.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Medicine, General & Internal
Ningbo Fei et al.
Summary: In this study, an automatic segmentation method based on ROI was proposed for the diagnosis of Cervical Spondylotic Myelopathy (CSM). The UNet model was trained with the proposed heatmap distance loss to accurately segment the spinal cord images. The ROI-based mean FA values showed strong correlation with the values based on manual drawing, indicating the potential of this method to quantify the detailed status of the cervical spinal cord.
Article
Computer Science, Artificial Intelligence
Mingjin Zhang et al.
Summary: This article addresses the problem of detecting hardware Trojan from microscope chip images. It proposes a novel MCI super-resolution method using a curvature consistent network, which can recover more delicate circuit lines and improve HT detection performance. Experiments on a new benchmark dataset called MCI demonstrate the superiority of the proposed method over representative SR methods. The MCI dataset is available on GitHub.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Wenhao Wu et al.
Summary: This paper proposes an infrared image super-resolution method using a lightweight network and meta-transfer learning. By designing a lightweight network to learn the mapping between low-resolution and high-resolution infrared images, and utilizing external dataset training and internal dataset meta-transfer learning, the method achieves better visual effects for infrared super-resolution images.
DIGITAL SIGNAL PROCESSING
(2022)
Article
Geochemistry & Geophysics
Aihua Zheng et al.
Summary: This article introduces a method called CaFE, which leverages category priors to achieve effective feature fusion and imbalance learning in multimodal remote sensing image semantic segmentation. The method disentangles the feature fusion process and assigns weights to category regions based on sample proportions, leading to improved segmentation results.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Information Systems
Zongyao He et al.
Summary: Recent years have witnessed the remarkable success of deep learning-based single image super-resolution (SISR) methods. However, most of the existing methods struggle with handling non-bicubic degradations. To address this issue, we propose a degradation reconstruction loss that captures the differences between degraded images and high-resolution images. Experimental results demonstrate that our method outperforms existing methods on multi-degraded datasets.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Article
Computer Science, Artificial Intelligence
Mike Huisman et al.
Summary: The text discusses the development of deep neural networks and meta-learning, summarizing key methods categorized into different techniques. It also points out the main challenges of meta-learning, such as performance evaluation and computational costs.
ARTIFICIAL INTELLIGENCE REVIEW
(2021)
Article
Computer Science, Artificial Intelligence
Wasif Arman Haque et al.
Summary: The paper presents a novel energy-efficient Thin yet Deep convolutional neural network architecture for traffic sign recognition with less than 50 features in each convolutional layer, achieving superior performance on two publicly available datasets.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Interdisciplinary Applications
Zhen Chen et al.
Summary: By proposing a framework that enhances medical image diagnosis using super-resolution techniques, this paper effectively utilizes global and local features. Through the joint use of original images and high-resolution images, and the introduction of new constraints, the diagnostic performance of medical images is significantly improved.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Environmental Sciences
Xubin Feng et al.
Summary: This study proposes a method based on Generative Adversarial Network for reconstructing high spatial quality remote sensing images, integrating denoising and super-resolution technology while fusing ResNet and DenseNet in the generative network. Total variation regularization is used to enhance edge details, and the concept of Relativistic GAN is explored for better network convergence. Experimental results demonstrate the feasibility of the proposed method in acquiring remote sensing images.
Proceedings Paper
Computer Science, Artificial Intelligence
Zhen Cheng et al.
Summary: A zero-shot learning framework is proposed to address the domain gap in light field super-resolution caused by different acquisition conditions, with simple and efficient CNNs tackling three sub-tasks separately. The new method outperforms classic non-learning methods and shows better generalization to unseen light fields when the domain gap is large.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Article
Computer Science, Information Systems
Qiong Ran et al.
MULTIMEDIA TOOLS AND APPLICATIONS
(2020)
Article
Geochemistry & Geophysics
Sen Lei et al.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Jae Woong Soh et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Article
Computer Science, Artificial Intelligence
Zhiyuan Zha et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2020)
Article
Environmental Sciences
Ying Liu et al.
Article
Geochemistry & Geophysics
Sen Lei et al.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2017)
Article
Engineering, Electrical & Electronic
Gong Cheng et al.
PROCEEDINGS OF THE IEEE
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Chao Dong et al.
COMPUTER VISION - ECCV 2014, PT IV
(2014)
