Article
Computer Science, Artificial Intelligence
Fabio Valerio Massoli, Fabio Carrara, Giuseppe Amato, Fabrizio Falchi
Summary: Adversarial detection techniques offer a solution to address the vulnerability of deep learning models to adversarial inputs without requiring model re-training, demonstrating generalizability and practicality in detecting different types of attacks.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2021)
Article
Computer Science, Information Systems
Gabriel Hermosilla, Diego-Ignacio Henriquez Tapia, Hector Allende-Cid, Gonzalo Farias Castro, Esteban Vera
Summary: This article utilizes StyleGAN2 and generative adversarial networks (GANs) to create high-quality synthetic thermal images and build thermal face recognition models using deep learning. By training with thermal databases and pretrained deep learning models, the synthetic thermal database achieved 99.98% accuracy in classifying thermal face images.
Article
Computer Science, Theory & Methods
Yingfan Tao, Wenxian Zheng, Wenming Yang, Guijin Wang, Qingmin Liao
Summary: A novel Frontal-Centers Guided Loss (FCGFace) is proposed for face recognition, which achieves better performance in handling profile faces. Compared to existing methods, FCGFace takes viewpoints into consideration and can adaptively adjust feature distribution to form compact identity clusters.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2022)
Article
Chemistry, Analytical
Ren-Hung Hwang, Jia-You Lin, Sun-Ying Hsieh, Hsuan-Yu Lin, Chia-Liang Lin
Summary: Deep learning technology has developed rapidly and has been successfully applied in various fields, including face recognition. However, most previous studies on adversarial attacks assume the attacker knows the architecture and parameters of the attacked deep learning model, which is not representative of real-world scenarios. This study proposes a Generative Adversarial Network method for generating adversarial patches to carry out dodging and impersonation attacks on a black-box face recognition system, achieving a higher attack success rate than previous works.
Article
Computer Science, Artificial Intelligence
Chaoyou Fu, Xiang Wu, Yibo Hu, Huaibo Huang, Ran He
Summary: In this paper, a novel method called DVG-Face is proposed to address the challenges in heterogeneous face recognition (HFR) through dual generation and contrastive learning mechanism. The method achieves superior performances on multiple HFR tasks, demonstrating its effectiveness.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Information Systems
Fatemeh Vakhshiteh, Ahmad Nickabadi, Raghavendra Ramachandra
Summary: Despite the reliable verification performance of face recognition systems, they have shown vulnerability to adversarial attacks prompting the development of new countermeasures. Existing attack and defense methods are classified based on different criteria, with a focus on the challenges and potential research directions ahead.
Article
Computer Science, Artificial Intelligence
Cuican Yu, Zihui Zhang, Huibin Li, Jian Sun, Zongben Xu
Summary: Recently, deep face recognition using 2D face images has advanced due to the availability of large-scale face data. However, deep face recognition using 3D face scans on point clouds still needs further exploration. This paper proposes a meta-learning-based adversarial training algorithm for deep 3D face recognition on point clouds. The algorithm combines adversarial sample generation and meta-learning-based network training to continuously generate diverse adversarial samples and improve the accuracy of the 3DFR model.
PATTERN RECOGNITION
(2023)
Article
Computer Science, Artificial Intelligence
Qingyan Duan, Lei Zhang, Yan Zhang, Xinbo Gao
Summary: This paper proposes a GAN-based face frontalization method using a Bayesian induced perceptual self-representation discriminator (PSD) to address the issues in traditional GANs. The proposed method reduces model parameters and training difficulty, and achieves superior performance.
Article
Computer Science, Artificial Intelligence
Decheng Liu, Xinbo Gao, Chunlei Peng, Nannan Wang, Jie Li
Summary: The article explores learning interpretable representations for complex heterogeneous faces and proposes the HFIDR and M-HFIDR methods for cross-modality recognition and synthesis tasks, achieving efficiency in face recognition and synthesis.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Theory & Methods
Min Ren, Yuhao Zhu, Yunlong Wang, Zhenan Sun
Summary: This paper proposes a plug-and-play defense method called perturbation inactivation (PIN) to improve the robustness of deep learning-based face recognition models against adversarial attacks. The method estimates an immune space in which adversarial perturbations have less impact on the recognition model and restricts the perturbations to this subspace. The method outperforms state-of-the-art defense methods and demonstrates good generalization capabilities in exhaustive experiments. It can also be easily applied to existing commercial APIs and face recognition systems.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2022)
Article
Computer Science, Information Systems
Le Minh Ngo, Sezer Karaoglu, Theo Gevers
Summary: A novel architecture is proposed in this paper for manipulating facial expressions, head poses, and lighting conditions from a single monocular image. The method outperforms state-of-the-art methods in various scenarios and does not require target specific training.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Article
Chemistry, Analytical
Caijie Zhao, Ying Qin, Bob Zhang
Summary: The ALOB model, which mitigates the need for manual labelling of occlusions, achieves excellent results in occluded face recognition by contrastively learning corrupted features against personal identity labels. It outperforms existing state-of-the-art methods in various experiments and demonstrates superior performance in masked face recognition and general face recognition.
Article
Computer Science, Artificial Intelligence
Wenjian Luo, Chenwang Wu, Li Ni, Nan Zhou, Zhenya Zhang
Summary: This paper proposes a positive-negative detector (PNDetector) to detect adversarial examples, and tests it on various datasets and attack types. The experimental results demonstrate that the proposed detector is highly effective in detecting adversarial examples and its detection performance is comparable to state-of-the-art methods.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Information Systems
Chih-Yang Lin, Feng-Jie Chen, Hui-Fuang Ng, Wei-Yang Lin
Summary: Deep learning technology has achieved great success in computer vision and has been widely applied in daily life, such as face recognition systems. However, the potential security risks of deep neural networks have been revealed, particularly in face recognition systems. Existing adversarial face images are easy to identify, making it difficult for attackers to carry out practical attacks.
Article
Computer Science, Information Systems
Burhan Ul haque Sheikh, Aasim Zafar
Summary: This article demonstrates the vulnerability of current deep learning-based face mask detection systems to adversarial attacks. A robust framework for face mask detection system is proposed to resist such attacks. The framework employs fine-tuning of the MobileNetV2 model on a custom-built dataset, achieving an accuracy of 95.83% on test data. Adversarial images generated by the fast gradient sign method (FGSM) significantly reduce the model's classification accuracy to 14.53%. However, the proposed robust framework enhances the model's resistance to adversarial attacks and achieves an accuracy of 92% on adversarial data.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Automation & Control Systems
Tianjiao Lin, Huaqing Wang, Xudong Guo, Pengxin Wang, Liuyang Song
Summary: This paper proposes a feature-transferred prediction network (FTPN) to improve the RUL prediction of CNC machine tools and other rotating machinery. The method combines the neural network approach in the field of artificial intelligence and adapt to various working conditions. By pre-training a convolutional neural network (CNN) for fault recognition and transferring the fault feature information to the target network, the proposed method achieves high prediction accuracy. Experimental results using a public data set of accelerated life of bearings demonstrate the effectiveness and industrial applicability of the proposed method.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2023)
Article
Environmental Sciences
Hui-ru Li, Xi-hang Fu, Ling-ling Song, Man-qiu Cen, Jing Wu
Summary: This study found an association between pyrethroid exposure and the risk of depressive symptoms. The levels of urinary 3-PBA were non-linearly related to the risk of depressive symptoms, and trouble sleeping may mediate this association.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Plant Sciences
Ruijiao Song, Xiangchi Zhang, Caijun Feng, Song Zhang, Lingyu Song, Juncang Qi
Summary: Hydrogen-rich water (HRW) pretreatment was found to improve germination and seedling establishment of barley under drought conditions. Additionally, HRW could mitigate drought-induced damage by activating sugar metabolism and regulating antioxidant balance.
JOURNAL OF PLANT GROWTH REGULATION
(2023)
Article
Ecology
Liyan Song, Yangqing Wang, Rui Zhang, Shu Yang
Summary: Landfills are important terrestrial ecosystems that act as significant carbon sinks. Microorganisms play a crucial role in the decomposition of solid waste, converting biodegradable substances into CH4, CO2, and microbial biomass. They also mediate the nitrogen and sulfur cycles, resulting in the emission of N2O and H2S. However, the response of microbial community structure and function to carbon, nitrogen, and sulfur cycling during solid waste decomposition is not well understood. In this study, we investigated the bacterial and archaeal community composition and functions during solid waste decomposition using molecular techniques. The results showed changes in the composition of bacterial and archaeal communities, as well as shifts in metabolic pathways and cycling processes. These findings highlight the extensive microbial mediation of carbon, nitrogen, and sulfur cycling profiles during solid waste decomposition.
Article
Neurosciences
Xihang Fu, Huiru Li, Xinzhen Chen, Jinliang Cai, Ting Yao, Lingling Song, Manqiu Cen, Jing Wu
Summary: This study found a negative linear association between urinary caffeine and caffeine metabolite levels and cognitive decline in older adults. The effects were more evident in men.
NUTRITIONAL NEUROSCIENCE
(2023)
Article
Chemistry, Organic
Liyan Song, Yiqin Zhou, Hanbin Liang, Hongzuo Li, Yunrong Lai, Hongliang Yao, Ran Lin, Rongbiao Tong
Summary: Semipinacol rearrangement is a valuable method for the synthesis of natural products and construction of highly congested quaternary carbons. Here, a safe and green protocol for halogenative semipinacol rearrangement is reported, which offers the advantages of easy operation and insensitivity to air and moisture.
JOURNAL OF ORGANIC CHEMISTRY
(2023)
Review
Dentistry, Oral Surgery & Medicine
Hanshu Yu, Luyao Song, Xiangyao Duan, Danji Zhu, Na Li, Runxin Pan, Rui Xu, Xinying Yu, Fengkai Ye, Xinrui Jiang, Han Ye, Zikang Pan, Sixing Wei, Zhiwei Jiang
Summary: The electrophysiological function of the tongue involves complex activities in taste perception of salty, sweet, bitter, and sour. Further fundamental research is needed for therapies and prevention of taste loss caused by dysfunction in electrophysiological activity. The application of optogenetics in taste research has revolutionized neuroscience and opened new opportunities for understanding sensory systems.
Article
Chemistry, Applied
Liying Song, Zhan Gao, Qiang Sun, Guiwen Chu, Hao Shi, Ningjing Xu, Zhenxing Li, Nini Hao, Xiaoying Zhang, Fubin Ma, Lifei Wang
Summary: Hollow mesoporous silica microspheres (HMSN) were used as carriers to store 2-aminino-5-mercato-1,3,4-thiadizole (ATM) in this experiment. The synthesised microspheres were uniformly dispersed with a diameter of approximately 500 nm, as confirmed by scanning electron microscopy. HMSN, as excellent nanocarriers, were employed to encapsulate ATM with a loading rate of 19 wt%. The addition of 18 wt% HMSN loaded with ATM to the coating improved the self-healing ability of the coating. Electrochemical impedance spectroscopy and scanning Kelvin probes were utilized to investigate the corrosion resistance of the coating.
PROGRESS IN ORGANIC COATINGS
(2023)
Article
Soil Science
Teng Yang, Luyao Song, Han-Yang Lin, Ke Dong, Xiao Fu, Gui-Feng Gao, Jonathan M. Adams, Haiyan Chu
Summary: The study found that plant phylogenetic relationships significantly influence fungal community structure in tree roots and surrounding soils. However, little research has been done on whether plant phylogenetic relationships within a single species can also affect fungal communities. The researchers surveyed ectomycorrhizal (EcM) and saprotrophic (SAP) fungal community structure in the fine roots and neighboring soils of Betula ermanii along the Changbai Mountain timberline. They found that within-species plant phylogeny was the main driver of EcM fungal community composition in roots, while geographic distance had the strongest influence on SAP fungal community composition in both soils and roots. Overall, the study shows that within-species plant phylogeny plays a crucial role in shaping EcM fungal communities in roots, and the assembly of fungal communities is dependent on both guild and habitat.
SOIL BIOLOGY & BIOCHEMISTRY
(2023)
Article
Biochemistry & Molecular Biology
Hui Shi, Jianhuan Li, Fei Liu, Sixue Bi, Weijuan Huang, Yuanyuan Luo, Man Zhang, Liyan Song, Rongmin Yu, Jianhua Zhu
Summary: A novel water-soluble alpha-d-glucan (ASPG-1) with immunoregulatory activity was purified and characterized from Arca subcrenata. ASPG-1 promoted lymphocyte viability, enhanced pinocytic capacity, and stimulated the secretion of NO and cytokines. It inhibited tumor growth in breast cancer mice and showed improved antitumor efficacy when combined with doxorubicin. Therefore, ASPG-1 has the potential to be developed as an adjuvant in tumor immunotherapy.
Article
Chemistry, Physical
Zhi-Qiang Wang, Xiao-Dong Liu, Hong-Ming Chen, Xiang-Yu Zhu, Li-Ying Song, Yun-Guo Yang, Jing Bai, M. J. Kim, Woon-Ming Lau, Federico Rosei, Dan Zhou
Summary: We report porous reduced graphene oxide boosted a-MnOx microspheres (PrGO-MnOx) as a cathode material for aqueous zinc ion batteries (AZIBs), which show a high capacity, high-rate capability, and ultra-long lifespan. The Zn-storage mechanism of PrGO-MnOx was elucidated via ex situ measurements, revealing the transformation of a-MnOx phase into amorphous Zn-buserite during initial cycles. The excellent performance of PrGO-MnOx was attributed to the amorphous structure of Zn-buserite, fast reaction kinetics, increased electron conductivity, improved Zn2+ diffusion rate, and high pseudocapacitance. A PrGO-MnOx||AQ full-battery also demonstrated impressive cycling stability and a high discharge plateau, suggesting its potential for practical applications.
JOURNAL OF MATERIALS CHEMISTRY A
(2023)
Article
Endocrinology & Metabolism
Wei Liu, Liying Song, Wei Sun, Weijin Fang, Chunjiang Wang
Summary: By retrospectively analyzing the distribution of pathogenic bacteria and antimicrobial susceptibility in 581 patients with diabetic foot infections (DFI), it was found that there were variations in the distribution of pathogens and drug susceptibility among patients with different Wagner grades, providing guidance for clinical empirical treatment and rational selection of antibacterial drugs.
FRONTIERS IN ENDOCRINOLOGY
(2023)
Article
Environmental Sciences
Liyan Song, Shu Yang, Zhourui Gong, Jun Wang, Xianyang Shi, Yangqing Wang, Rui Zhang, Yongchun Wu, Yongli Z. Wager
Summary: This review provides an overview of the global status of antibiotics and antibiotic resistance, and offers recommendations for future research directions, including long-term antibiotic resistance environmental behavior, multidrug resistance gene distribution and dynamics, link between antibiotic resistance and the host, coevolution of ARGs and microplastics as emerging contaminants, antibiotic resistance risk assessment, and towards a one health framework in the landfill system.
CURRENT OPINION IN ENVIRONMENTAL SCIENCE & HEALTH
(2023)
Article
Plant Sciences
Huan-Yi Xu, Quan-Cen Li, Wen-Jie Zhou, Hai-Bo Zhang, Zhi-Xian Chen, Ning Peng, Shi-Yu Gong, Bin Liu, Feng Zeng
Summary: The antioxidative and antiaging abilities of probiotic fermented ginseng (PG) were evaluated in Caenorhabditis elegans (C. elegans). The results showed that PG significantly enhanced the lifespan of C. elegans and improved their resistance to heat stress and acute oxidative stress. The mechanism behind these activities was found to involve up-regulation of antioxidative enzymes and down-regulation of oxidative stress markers. Furthermore, PG was found to modulate gut microbiota composition, increase the abundance of beneficial bacteria, and regulate metabolic pathways related to antioxidant and antiaging activities in C. elegans.
PLANT FOODS FOR HUMAN NUTRITION
(2023)
Article
Materials Science, Multidisciplinary
Yinkai Shi, Hua Yu, Shizhong Wei, Weimin Long, Yunpeng Li, Liangliang Zhang, Xinna Cao, Lingling Huang, Luyang Song, Zhuoli Yu, Sujuan Zhong, Yongtao Jiu, Yunfeng Chang
Summary: The purpose of this article was to provide a theoretical basis for the manufacture and practical working application of metal composite plates by simulating the influence of post-weld heat treatment on the interfacial characteristics, microstructure, composition, and mechanical properties of copper/steel composite plates. The study investigated the microstructure and melting properties of BAg30T filler metal and evaluated the effect of heat treatment on the microstructure and mechanical properties of Cu-Fe dissimilar metal joints. The results showed significant changes in the microstructure and mechanical properties of the joints, and the PWHT process at 600 degrees C improved the tensile strength of the brazed joint.
MATERIALS TODAY COMMUNICATIONS
(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)