Article
Biology
Khalid M. Hosny, Asmaa M. Khalid, Hanaa M. Hamza, Seyedali Mirjalili
Summary: Medical image segmentation is a crucial step in Computer-Aided Diagnosis systems. This study proposed a multilevel thresholding technique that improved upon existing algorithms by hybridizing the Coronavirus Optimization Algorithm and the Harris Hawks Optimization Algorithm. The proposed algorithm demonstrated superior performance in terms of convergence to the global optimum and the quality of segmented images.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Computer Science, Artificial Intelligence
Xiancai Kang, Chuangli Hua
Summary: Image segmentation is an important task in computer vision and computer image processing. This study proposes a multi-level threshold image segmentation algorithm based on the MSh model, which significantly improves the segmentation effect, increases runtime efficiency, and reduces segmentation time.
JOURNAL OF INTELLIGENT SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Nilima Shah, Dhanesh Patel, Pasi Franti
Summary: The study introduces how to integrate the Mumford-Shah model into the k-means algorithm to optimize the content and shape of image segmentation simultaneously. The experiments demonstrate that the proposed method provides better results compared to comparative methods.
JOURNAL OF ELECTRONIC IMAGING
(2021)
Article
Mathematics, Applied
Jyrki Jauhiainen, Aku Seppanen, Tuomo Valkonen
Summary: Electrical impedance tomography (EIT) is a method that aims to determine the conductivity within a target body by measuring electrical signals on its surface. The inverse conductivity problem is challenging due to limited measurement data, hence requiring regularization. Traditional regularization methods focus on promoting smooth features, but for targets consisting of multiple distinct objects or materials, the Mumford-Shah (M-S) regularization familiar in image segmentation is more suitable. However, it poses numerical challenges. The study shows through theoretical analysis that a modification of the Ambrosio-Tortorelli approximation of the M-S regularizer is applicable to EIT, specifically in the complete electrode model of boundary measurements. Numerical and experimental studies confirm the practicality of this approach, producing higher quality results compared to typical regularizations employed in EIT when the conductivity of the target consists of distinct smoothly-varying regions.
Article
Engineering, Electrical & Electronic
Wenxiu Zhao, Weiwei Wang, Xiangchu Feng, Yu Han
Summary: Selective segmentation is crucial in medical image analysis, and this paper presents a two-phase method using a new image smoothing model and a modified active contour method to achieve efficient and accurate segmentation outcomes. The proposed approach significantly improves existing methods and facilitates the segmentation process.
Article
Computer Science, Artificial Intelligence
Muhammad Shahkar Khan, Haider Ali, Muhammad Zakarya, Santosh Tirunagari, Ayaz Ali Khan, Rahim Khan, Aftab Ahmed, Lavdie Rada
Summary: In this article, a novel variational model is proposed for concurrent restoration and segmentation of noisy images with intensity inhomogeneity and high contrast background illumination. The model combines multi-phase segmentation technology with a statistical approach to enable inhomogeneous image restoration. Through tests and simulations, the proposed model is shown to outperform cutting-edge two-phase and multi-phase methods in accurately segmenting images with noise, background light, and inhomogeneity.
Article
Computer Science, Artificial Intelligence
Monika Muszkieta
Summary: In this paper, we propose an approach for automated image restoration and segmentation by considering Mumford-Shah-like regularization and utilizing topological asymptotic analysis. We prove the existence of minimizers for the proposed functional and develop a method for their computation. Additionally, we introduce new criteria for selecting optimal values of two regularization parameters in the model. The effectiveness of the method is demonstrated through numerical experiments on synthetic and real test images.
JOURNAL OF MATHEMATICAL IMAGING AND VISION
(2022)
Article
Engineering, Biomedical
J. Ramya, H. C. Vijaylakshmi, Huda Mirza Saifuddin
Summary: The proposed method in this paper utilizes discrete wavelet transform for skin lesion segmentation, effectively addressing the complexities in dermoscopic images. By analyzing color components and using thresholding techniques, the method separates skin lesion region from background with promising results. Experimental comparisons with state-of-the-art methods demonstrate the effectiveness and superiority of the proposed method.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Computer Science, Artificial Intelligence
R. Premalatha, P. Dhanalakshmi
Summary: The current research explores object enhancement and segmentation for CT images of lungs infected with COVID-19 using Pythagorean fuzzy entropy, measures, and thresholding technique. The proposed scheme shows the best effect on object separation and quality measurement values compared to other segmentation algorithms in terms of object extraction ability.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Mohammad Otair, Laith Abualigah, Saif Tawfiq, Mohammad Alshinwan, Absalom E. Ezugwu, Raed Abu Zitar, Putra Sumari
Summary: In recent years, the determination of the ideal thresholding for picture segmentation has attracted increasing interest. However, existing techniques face issues such as long calculation times, high computational costs, and the need for accuracy improvements when finding appropriate thresholds for multilevel thresholding. This study investigates the capability of the Arithmetic Optimization Algorithm (AOA) to discover the best multilayer thresholding for picture segmentation. The AOA method utilizes the distributional nature of mathematical arithmetic operators and constructs candidate solutions based on the picture histogram, which are then updated according to the algorithm's features. The proposed approach is tested and evaluated against other well-known optimization methods using various assessment metrics.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Tejna Khosla, Om Prakash Verma
Summary: Image segmentation is a significant area in image processing, and accurately segmenting medical images is a crucial step in medical image analysis. To address this challenge, a novel image segmentation technique named CSAPSO based on the features of OBL, CSA, and PSO is proposed. It is evaluated on CXR images for pneumonia detection and compared with state-of-the-art methods, demonstrating better global optimal results.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Lin Lan, Shengsheng Wang
Summary: In this study, a multi-level threshold image segmentation method based on African vultures optimization algorithm (OLAVOA) is proposed. The 2D Kapur's entropy is employed as a fitness value function to solve the issues in the traditional methods. The experimental results demonstrate that OLAVOA outperforms other algorithms in multi-threshold image segmentation, showing good convergence speed and ability to depart from local optima. Furthermore, the effectiveness and adaptability of OLAVOA in medical image segmentation are demonstrated through experiments.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Angang Cui, Haizhen He, Zhiqi Xie, Weijun Yan, Hong Yang
Summary: This paper studies a nonconvex surrogate function, Laplace norm, for recovering sparse signals. Firstly, the equivalence of the optimal solutions of $l_0$-norm minimization problem, Laplace norm minimization problem, and regularization Laplace norm minimization problem is discussed. It is proven that the $l_0$-norm minimization problem can be solved by solving the regularization Laplace norm minimization problem under certain conditions. Secondly, an iterative difference hard-thresholding algorithm and its adaptive version algorithm are proposed to solve the regularization Laplace norm minimization problem. Finally, numerical experiments are provided to test the performance of the adaptive iterative difference hard-thresholding algorithm, and the results show that it outperforms some state-of-the-art methods in recovering sparse signals.
IEEE TRANSACTIONS ON SIGNAL PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Michael Hintermueller, Steven-Marian Stengl, Thomas M. Surowiec
Summary: This study focuses on quantifying uncertainties in image segmentation based on the Mumford-Shah model, specifically addressing error propagation from noise and other error types in the original image to the restoration result, particularly in reconstructed edges. Analytically, the Ambrosio-Tortorelli approximation is utilized to discuss the existence of measurable selections for solutions, as well as sampling-based methods and limitations of other popular approaches. Numerical examples are provided to illustrate the theoretical findings.
JOURNAL OF MATHEMATICAL IMAGING AND VISION
(2021)
Review
Computer Science, Interdisciplinary Applications
Amrita Kaur, Yadwinder Singh, Nirvair Neeru, Lakhwinder Kaur, Ashima Singh
Summary: The article provides an overview of machine learning and deep learning, focusing on their applications in medical imaging and object detection. It discusses the rapid developments in deep learning techniques and the widespread use of deep neural networks in various fields. The importance and challenges of object detection, as well as future research directions, are also explored in the article.
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING
(2022)
Article
Mathematics, Applied
Xue-lei Lin, Xin Huang, Michael K. Ng, Hai-Wei Sun
Summary: In this paper, a tau-preconditioner for non-symmetric linear systems arising from a multi-dimensional Riemann-Liouville fractional diffusion equation is studied. The proposed iterative solver achieves a convergence rate independent of discretization stepsizes and utilizes fast matrix-vector multiplication through the fast sine transform. Numerical results demonstrate the efficiency of the proposed preconditioner.
NUMERICAL ALGORITHMS
(2023)
Article
Computer Science, Interdisciplinary Applications
Zhifan Gao, Yifeng Guo, Jiajing Zhang, Tieyong Zeng, Guang Yang
Summary: The long acquisition time of magnetic resonance imaging (MRI) has been a limitation in terms of patient comfort and motion artifacts. Compressed sensing in MRI (CS-MRI) has enabled fast acquisition without compromising SNR and resolution, but current CS-MRI methods struggle with aliasing artifacts, leading to unsatisfactory reconstruction performance. In order to address this challenge, a hierarchical perception adversarial learning framework (HP-ALF) is proposed. HP-ALF utilizes a hierarchical mechanism to perceive image information and effectively removes aliasing artifacts while recovering fine details.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2023)
Article
Computer Science, Artificial Intelligence
Jun Liu, Ryan Wen Liu, Jianing Sun, Tieyong Zeng
Summary: In this article, a new real-time scene recovery framework is proposed to restore degraded images under different weather/imaging conditions. The method introduces a rank-one matrix to characterize the degradation phenomenon and achieves real-time recovery. Experimental results demonstrate that the proposed method outperforms several state-of-the-art imaging methods in terms of efficiency and robustness.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Mathematics, Applied
Wei-Wei Xu, Michael K. Ng
Summary: A High-Order Generalized Singular Value Decomposition (HO-GSVD) is used to compare multiple matrices {Ai} (N) (i=1) with different row dimensions by examining their generalized singular values {sigma i, k} Ni=1. The significance of the k-th basis vector on the right hand side of the matrix from HO-GSVD for multiple matrices {A(i)} (N) (i=1) can be determined by the ratio values of sigma(i, k)/sigma(j, k). This paper proposes and studies a new matrix maximization model for computing these ratio values from A(1), ..., A(N), which can be solved using the Newton method on Lie Groups with well-defined initial values. Numerical examples are provided to demonstrate the fast performance of the proposed method in solving the optimization model compared to existing algorithms and the Riemannian Newton method.
JOURNAL OF SCIENTIFIC COMPUTING
(2023)
Article
Engineering, Electrical & Electronic
Zhi-Feng Pang, Mengxiao Geng, Lan Zhang, Yanru Zhou, Tieyong Zeng, Liyun Zheng, Na Zhang, Dong Liang, Hairong Zheng, Yongming Dai, Zhenxing Huang, Zhanli Hu
Summary: In this study, an adaptive weighted curvature-based active contour model is proposed for medical image segmentation, which combines heat kernel convolution and adaptively weighted high-order total variation. The experimental results demonstrate that the proposed method is more efficient and robust compared to traditional segmentation methods.
Article
Mathematics, Applied
Junren Chen, Michael K. Ng
Summary: This paper investigates the phase-only reconstruction problem, focusing on recovering a complex-valued signal x in Cd from the phase of Ax. Uniqueness conditions are derived using discriminant matrices, determining if the signal can be uniquely reconstructed. The minimum measurement number is also examined, with at least 2d but no more than 4d-2 measurements needed for reconstruction of all x∈Cd. Practical and general uniqueness conditions are provided for the phase-only reconstruction in Rd, and the results can be extended to affine phase-only reconstruction where the phase of Ax + b is observed for some b∈Cm.
SIAM JOURNAL ON APPLIED MATHEMATICS
(2023)
Article
Mathematics, Applied
Junjun Pan, Michael K. Ng
Summary: This paper introduces the nonnegative matrix factorization model (NMF) and its extended form, coseparable NMF (CoS-NMF), and studies their mathematical properties and relationships with other matrix factorization methods. The paper also proposes an optimization method for CoS-NMF and verifies its effectiveness and superiority through experiments.
SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Wen Yu, Baiying Lei, Shuqiang Wang, Yong Liu, Zhiguang Feng, Yong Hu, Yanyan Shen, Michael K. Ng
Summary: In this study, a multidirectional perception generative adversarial network (MP-GAN) is proposed to visualize the morphological features of patients with early stages of Alzheimer's disease (AD), indicating the severity of the disease. Experimental results demonstrate that MP-GAN outperforms existing methods and the visualized lesions are consistent with what clinicians observe.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Lina Zhuang, Michael K. Ng
Summary: This article introduces a fast and parameter-free method for removing mixed noise in hyperspectral images. The method models the complex distribution of mixed noise using a Gaussian mixture model and utilizes the low rankness and spatial correlation of hyperspectral data to remove noise. Experimental results demonstrate significant improvement in both synthetic and real datasets.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Information Systems
Jian Guan, Ming Fan, Tieyong Zeng, Lihua Li
Summary: Assessments of multiple clinical indicators based on radiomic analysis of MRI are beneficial to breast cancer patients. This study proposes a multilabel learning method that learns common and task-specific features using label space dimensionality reduction and nonnegative matrix factorization, and builds a multilabel classification to predict clinical indicators. Experimental results show that the proposed method outperforms other methods in predicting multiple indicators.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Mathematics, Applied
Yun-Yang Liu, Xi-Le Zhao, Guang-Jing Song, Yu-Bang Zheng, Michael K. Ng, Ting-Zhu Huang
Summary: Motivated by the success of fully-connected tensor network (FCTN) decomposition, this study proposes two FCTN-based models for the robust tensor completion (RTC) problem. The first model, named RNC-FCTN, directly applies FCTN decomposition for the RTC problem. An algorithm based on proximal alternating minimization (PAM) is developed to solve RNC-FCTN. The second model, named RC-FCTN, uses the FCTN nuclear norm as a convex surrogate function and applies robust convex optimization for RTC. An algorithm based on alternating direction method of multipliers (ADMM) is developed for RC-FCTN.
INVERSE PROBLEMS AND IMAGING
(2023)
Article
Mathematics, Applied
Huanmin Ge, Wengu Chen, Michael K. Ng
Summary: In this paper, we propose a novel model, the weighted l(1)/l(2) minimization, which incorporates partial support information into the standard l(1)/l(2) minimization to recover sparse signals from linear measurements. We establish the restricted isometry property based conditions for sparse signal recovery using the weighted l(1)/l(2) minimization in both noiseless and noisy cases. Our results show that these conditions are weaker than the analogous conditions for standard l(1)/l(2) minimization when the accuracy of the partial support information is at least 50%. Additionally, we develop effective algorithms and validate our results through extensive numerical experiments using synthetic data in both noiseless and noisy cases.
INFORMATION AND INFERENCE-A JOURNAL OF THE IMA
(2023)
Article
Computer Science, Artificial Intelligence
Hanrui Wu, Yuguang Yan, Michael Kwok-Po Ng
Summary: In this paper, a novel model called Hypergraph Collaborative Network (HCoN) is proposed, which considers the information from both previous vertices and hyperedges to achieve informative latent representations and introduces the hypergraph reconstruction error as a regularizer to learn an effective classifier. Experimental results demonstrate that the proposed method outperforms the baseline methods.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Engineering, Electrical & Electronic
Junren Chen, Yueqi Wang, Michael K. Ng
Summary: This paper investigates quantized LRMR and proposes estimators using uniform quantization with random dithering. Non-asymptotic error bounds are derived and the results are corroborated through simulations.
IEEE TRANSACTIONS ON SIGNAL PROCESSING
(2023)
Article
Geochemistry & Geophysics
Zhicheng Wang, Michael K. Ng, Joseph Michalski, Lina Zhuang
Summary: This article proposes a new framework for HSI and MSI fusion, in which a self-supervised deep learning prior is plugged into the ADMM framework using the plug-and-play technique. Experimental results show that the proposed method outperforms other fusion methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
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)