Artificial intelligence(AI)models have significantly impacted various areas of the atmospheric sciences,reshaping our approach to climate-related challenges.Amid this AI-driven transformation,the foundational role of ...Artificial intelligence(AI)models have significantly impacted various areas of the atmospheric sciences,reshaping our approach to climate-related challenges.Amid this AI-driven transformation,the foundational role of physics in climate science has occasionally been overlooked.Our perspective suggests that the future of climate modeling involves a synergistic partnership between AI and physics,rather than an“either/or”scenario.Scrutinizing controversies around current physical inconsistencies in large AI models,we stress the critical need for detailed dynamic diagnostics and physical constraints.Furthermore,we provide illustrative examples to guide future assessments and constraints for AI models.Regarding AI integration with numerical models,we argue that offline AI parameterization schemes may fall short of achieving global optimality,emphasizing the importance of constructing online schemes.Additionally,we highlight the significance of fostering a community culture and propose the OCR(Open,Comparable,Reproducible)principles.Through a better community culture and a deep integration of physics and AI,we contend that developing a learnable climate model,balancing AI and physics,is an achievable goal.展开更多
In recent years,various adversarial defense methods have been proposed to improve the robustness of deep neural networks.Adversarial training is one of the most potent methods to defend against adversarial attacks.How...In recent years,various adversarial defense methods have been proposed to improve the robustness of deep neural networks.Adversarial training is one of the most potent methods to defend against adversarial attacks.However,the difference in the feature space between natural and adversarial examples hinders the accuracy and robustness of the model in adversarial training.This paper proposes a learnable distribution adversarial training method,aiming to construct the same distribution for training data utilizing the Gaussian mixture model.The distribution centroid is built to classify samples and constrain the distribution of the sample features.The natural and adversarial examples are pushed to the same distribution centroid to improve the accuracy and robustness of the model.The proposed method generates adversarial examples to close the distribution gap between the natural and adversarial examples through an attack algorithm explicitly designed for adversarial training.This algorithm gradually increases the accuracy and robustness of the model by scaling perturbation.Finally,the proposed method outputs the predicted labels and the distance between the sample and the distribution centroid.The distribution characteristics of the samples can be utilized to detect adversarial cases that can potentially evade the model defense.The effectiveness of the proposed method is demonstrated through comprehensive experiments.展开更多
Adversarial distillation(AD)has emerged as a potential solution to tackle the challenging optimization problem of loss with hard labels in adversarial training.However,fixed sample-agnostic and student-egocentric atta...Adversarial distillation(AD)has emerged as a potential solution to tackle the challenging optimization problem of loss with hard labels in adversarial training.However,fixed sample-agnostic and student-egocentric attack strategies are unsuitable for distillation.Additionally,the reliability of guidance from static teachers diminishes as target models become more robust.This paper proposes an AD method called Learnable Distillation Attack Strategies and Evolvable Teachers Adversarial Distillation(LDAS&ET-AD).Firstly,a learnable distillation attack strategies generating mechanism is developed to automatically generate sample-dependent attack strategies tailored for distillation.A strategy model is introduced to produce attack strategies that enable adversarial examples(AEs)to be created in areas where the target model significantly diverges from the teachers by competing with the target model in minimizing or maximizing the AD loss.Secondly,a teacher evolution strategy is introduced to enhance the reliability and effectiveness of knowledge in improving the generalization performance of the target model.By calculating the experimentally updated target model’s validation performance on both clean samples and AEs,the impact of distillation from each training sample and AE on the target model’s generalization and robustness abilities is assessed to serve as feedback to fine-tune standard and robust teachers accordingly.Experiments evaluate the performance of LDAS&ET-AD against different adversarial attacks on the CIFAR-10 and CIFAR-100 datasets.The experimental results demonstrate that the proposed method achieves a robust precision of 45.39%and 42.63%against AutoAttack(AA)on the CIFAR-10 dataset for ResNet-18 and MobileNet-V2,respectively,marking an improvement of 2.31%and 3.49%over the baseline method.In comparison to state-of-the-art adversarial defense techniques,our method surpasses Introspective Adversarial Distillation,the top-performing method in terms of robustness under AA attack for the CIFAR-10 dataset,with enhancements of 1.40%and 1.43%for ResNet-18 and MobileNet-V2,respectively.These findings demonstrate the effectiveness of our proposed method in enhancing the robustness of deep learning networks(DNNs)against prevalent adversarial attacks when compared to other competing methods.In conclusion,LDAS&ET-AD provides reliable and informative soft labels to one of the most promising defense methods,AT,alleviating the limitations of untrusted teachers and unsuitable AEs in existing AD techniques.We hope this paper promotes the development of DNNs in real-world trust-sensitive fields and helps ensure a more secure and dependable future for artificial intelligence systems.展开更多
This study examines the relationship between discourse intonation （henceforth DI） and teacher cognition. Drawing on the rich literature on the teacher cognition in grammar, this study borrows some relevant insights ...This study examines the relationship between discourse intonation （henceforth DI） and teacher cognition. Drawing on the rich literature on the teacher cognition in grammar, this study borrows some relevant insights for a better understanding of the relationship between teacher cognition and DI. Following a qualitative treatment, the study concludes that instruction on D1 is a dynamic debate fed by both teacher training and teachers＇ experience of teaching and learning in general, which leads into suggesting the need for any teacher training on DI to take into account both DI knowledge as well as teacher core and peripheral belief. The contribution of the study lies in its tapping of a relatively poorly investigated area and offering advances on the many negative or simplistic teacher attitudes regarding intonation instruction as expressed in the literature, as well as in bringing to the surfaces something which teachers sometimes are not explicitly aware of.展开更多
How can the education of teacher-researchers from China be framed in ways so that they might make Chinese learnable for primary and secondary school learners for whom English is their everyday language of instruction ...How can the education of teacher-researchers from China be framed in ways so that they might make Chinese learnable for primary and secondary school learners for whom English is their everyday language of instruction and communication.The concept“making Chinese learnable”and the characters of the language learners are explained in the introduction to the paper.The review of an extensive range of literature focuses on the challenges facing Chinese language education.This review of literature from China,the UK,the USA,and Australia leads to a focus on the need for improved teacher education in this field.We explain the theoretic-pedagogical framework for the education of Chinese language teacher-researchers from China.The“case”employed to develop this account an Australia-China partnership called the Research Oriented,School/Industry Engaged Teacher-Researcher Education(ROSETE)Program.Key aspects relating to the educational research process employed in this study are explained.The description of the ROSETE Program introduces the key ideas of“cross-sociolinguistic similarities”and“recurring everyday sociolinguistic activities.”The Ningbo Volunteers,as teacher-researcher candidates use these ideas to investigate efficient ways of making Chinese learnable for learners in Australian schools for whom English is their everyday language of instruction and communication.Through exploring these issues this paper addresses an important and under researched area.It provides inspiration for further teaching and research.展开更多
Restricted by the lighting conditions,the images captured at night tend to sufer from color aberration,noise,and other unfavorable factors,making it difcult for subsequent vision-based applications.To solve this probl...Restricted by the lighting conditions,the images captured at night tend to sufer from color aberration,noise,and other unfavorable factors,making it difcult for subsequent vision-based applications.To solve this problem,we propose a two-stage size-controllable low-light enhancement method,named Dual Fusion Enhancement Net(DFEN).The whole algorithm is built on a double U-Net structure,implementing brightness adjustment and detail revision respectively.A dual branch feature fusion module is adopted to enhance its ability of feature extraction and aggregation.We also design a learnable regularized attention module to balance the enhancement efect on diferent regions.Besides,we introduce a cosine training strategy to smooth the transition of the training target from the brightness adjustment stage to the detail revision stage during the training process.The proposed DFEN is tested on several low-light datasets,and the experimental results demonstrate that the algorithm achieves superior enhancement results with the similar parameters.It is worth noting that the lightest DFEN model reaches 11 FPS for image size of 1224×10^(24)in an RTX 3090 GPU.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.42141019 and 42261144687)and STEP(Grant No.2019QZKK0102)supported by the Korea Environmental Industry&Technology Institute(KEITI)through the“Project for developing an observation-based GHG emissions geospatial information map”,funded by the Korea Ministry of Environment(MOE)(Grant No.RS-2023-00232066).
文摘Artificial intelligence(AI)models have significantly impacted various areas of the atmospheric sciences,reshaping our approach to climate-related challenges.Amid this AI-driven transformation,the foundational role of physics in climate science has occasionally been overlooked.Our perspective suggests that the future of climate modeling involves a synergistic partnership between AI and physics,rather than an“either/or”scenario.Scrutinizing controversies around current physical inconsistencies in large AI models,we stress the critical need for detailed dynamic diagnostics and physical constraints.Furthermore,we provide illustrative examples to guide future assessments and constraints for AI models.Regarding AI integration with numerical models,we argue that offline AI parameterization schemes may fall short of achieving global optimality,emphasizing the importance of constructing online schemes.Additionally,we highlight the significance of fostering a community culture and propose the OCR(Open,Comparable,Reproducible)principles.Through a better community culture and a deep integration of physics and AI,we contend that developing a learnable climate model,balancing AI and physics,is an achievable goal.
基金supported by the National Natural Science Foundation of China(No.U21B2003,62072250,62072250,62172435,U1804263,U20B2065,61872203,71802110,61802212)the National Key R&D Program of China(No.2021QY0700)+4 种基金the Key Laboratory of Intelligent Support Technology for Complex Environments(Nanjing University of Information Science and Technology),Ministry of Education,and the Natural Science Foundation of Jiangsu Province(No.BK20200750)Open Foundation of Henan Key Laboratory of Cyberspace Situation Awareness(No.HNTS2022002)Post Graduate Research&Practice Innvoation Program of Jiangsu Province(No.KYCX200974)Open Project Fund of Shandong Provincial Key Laboratory of Computer Network(No.SDKLCN-2022-05)the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)Fund and Graduate Student Scientific Research Innovation Projects of Jiangsu Province(No.KYCX231359).
文摘In recent years,various adversarial defense methods have been proposed to improve the robustness of deep neural networks.Adversarial training is one of the most potent methods to defend against adversarial attacks.However,the difference in the feature space between natural and adversarial examples hinders the accuracy and robustness of the model in adversarial training.This paper proposes a learnable distribution adversarial training method,aiming to construct the same distribution for training data utilizing the Gaussian mixture model.The distribution centroid is built to classify samples and constrain the distribution of the sample features.The natural and adversarial examples are pushed to the same distribution centroid to improve the accuracy and robustness of the model.The proposed method generates adversarial examples to close the distribution gap between the natural and adversarial examples through an attack algorithm explicitly designed for adversarial training.This algorithm gradually increases the accuracy and robustness of the model by scaling perturbation.Finally,the proposed method outputs the predicted labels and the distance between the sample and the distribution centroid.The distribution characteristics of the samples can be utilized to detect adversarial cases that can potentially evade the model defense.The effectiveness of the proposed method is demonstrated through comprehensive experiments.
基金the National Key Research and Development Program of China(2021YFB1006200)Major Science and Technology Project of Henan Province in China(221100211200).Grant was received by S.Li.
文摘Adversarial distillation(AD)has emerged as a potential solution to tackle the challenging optimization problem of loss with hard labels in adversarial training.However,fixed sample-agnostic and student-egocentric attack strategies are unsuitable for distillation.Additionally,the reliability of guidance from static teachers diminishes as target models become more robust.This paper proposes an AD method called Learnable Distillation Attack Strategies and Evolvable Teachers Adversarial Distillation(LDAS&ET-AD).Firstly,a learnable distillation attack strategies generating mechanism is developed to automatically generate sample-dependent attack strategies tailored for distillation.A strategy model is introduced to produce attack strategies that enable adversarial examples(AEs)to be created in areas where the target model significantly diverges from the teachers by competing with the target model in minimizing or maximizing the AD loss.Secondly,a teacher evolution strategy is introduced to enhance the reliability and effectiveness of knowledge in improving the generalization performance of the target model.By calculating the experimentally updated target model’s validation performance on both clean samples and AEs,the impact of distillation from each training sample and AE on the target model’s generalization and robustness abilities is assessed to serve as feedback to fine-tune standard and robust teachers accordingly.Experiments evaluate the performance of LDAS&ET-AD against different adversarial attacks on the CIFAR-10 and CIFAR-100 datasets.The experimental results demonstrate that the proposed method achieves a robust precision of 45.39%and 42.63%against AutoAttack(AA)on the CIFAR-10 dataset for ResNet-18 and MobileNet-V2,respectively,marking an improvement of 2.31%and 3.49%over the baseline method.In comparison to state-of-the-art adversarial defense techniques,our method surpasses Introspective Adversarial Distillation,the top-performing method in terms of robustness under AA attack for the CIFAR-10 dataset,with enhancements of 1.40%and 1.43%for ResNet-18 and MobileNet-V2,respectively.These findings demonstrate the effectiveness of our proposed method in enhancing the robustness of deep learning networks(DNNs)against prevalent adversarial attacks when compared to other competing methods.In conclusion,LDAS&ET-AD provides reliable and informative soft labels to one of the most promising defense methods,AT,alleviating the limitations of untrusted teachers and unsuitable AEs in existing AD techniques.We hope this paper promotes the development of DNNs in real-world trust-sensitive fields and helps ensure a more secure and dependable future for artificial intelligence systems.
基金supported by the Frontier Leading Technology Basic Research Project of Jiangsu(BK20202007)the National Natural Science Foundation of China(52175330)the Fundamental Research Funds for the Central Universities(30921011202).
文摘This study examines the relationship between discourse intonation （henceforth DI） and teacher cognition. Drawing on the rich literature on the teacher cognition in grammar, this study borrows some relevant insights for a better understanding of the relationship between teacher cognition and DI. Following a qualitative treatment, the study concludes that instruction on D1 is a dynamic debate fed by both teacher training and teachers＇ experience of teaching and learning in general, which leads into suggesting the need for any teacher training on DI to take into account both DI knowledge as well as teacher core and peripheral belief. The contribution of the study lies in its tapping of a relatively poorly investigated area and offering advances on the many negative or simplistic teacher attitudes regarding intonation instruction as expressed in the literature, as well as in bringing to the surfaces something which teachers sometimes are not explicitly aware of.
文摘How can the education of teacher-researchers from China be framed in ways so that they might make Chinese learnable for primary and secondary school learners for whom English is their everyday language of instruction and communication.The concept“making Chinese learnable”and the characters of the language learners are explained in the introduction to the paper.The review of an extensive range of literature focuses on the challenges facing Chinese language education.This review of literature from China,the UK,the USA,and Australia leads to a focus on the need for improved teacher education in this field.We explain the theoretic-pedagogical framework for the education of Chinese language teacher-researchers from China.The“case”employed to develop this account an Australia-China partnership called the Research Oriented,School/Industry Engaged Teacher-Researcher Education(ROSETE)Program.Key aspects relating to the educational research process employed in this study are explained.The description of the ROSETE Program introduces the key ideas of“cross-sociolinguistic similarities”and“recurring everyday sociolinguistic activities.”The Ningbo Volunteers,as teacher-researcher candidates use these ideas to investigate efficient ways of making Chinese learnable for learners in Australian schools for whom English is their everyday language of instruction and communication.Through exploring these issues this paper addresses an important and under researched area.It provides inspiration for further teaching and research.
基金supported by State Grid Corporation of China(5700-202325308A-1-1-ZN)Information&Telecommunication Branch of State Grid Jiangxi Electric Power Company.
文摘Restricted by the lighting conditions,the images captured at night tend to sufer from color aberration,noise,and other unfavorable factors,making it difcult for subsequent vision-based applications.To solve this problem,we propose a two-stage size-controllable low-light enhancement method,named Dual Fusion Enhancement Net(DFEN).The whole algorithm is built on a double U-Net structure,implementing brightness adjustment and detail revision respectively.A dual branch feature fusion module is adopted to enhance its ability of feature extraction and aggregation.We also design a learnable regularized attention module to balance the enhancement efect on diferent regions.Besides,we introduce a cosine training strategy to smooth the transition of the training target from the brightness adjustment stage to the detail revision stage during the training process.The proposed DFEN is tested on several low-light datasets,and the experimental results demonstrate that the algorithm achieves superior enhancement results with the similar parameters.It is worth noting that the lightest DFEN model reaches 11 FPS for image size of 1224×10^(24)in an RTX 3090 GPU.
