Log in

Relevant bibliographies by topics / Adaptive Sharpness Aware Minimization / Journal articles

To see the other types of publications on this topic, follow the link: Adaptive Sharpness Aware Minimization.

Journal articles on the topic 'Adaptive Sharpness Aware Minimization'

Author: Grafiati

Published: 10 December 2022

Last updated: 31 July 2025

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the top 50 journal articles for your research on the topic 'Adaptive Sharpness Aware Minimization.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.

1

Ratchatorn, Tanapat, and Masayuki Tanaka. "Improving Sharpness-Aware Minimization Using Label Smoothing and Adaptive Adversarial Cross-Entropy Loss." IEEE Access 13 (2025): 100326–37. https://doi.org/10.1109/access.2025.3578265.

Full text

APA, Harvard, Vancouver, ISO, and other styles

2

Dong, Mingrong, Yixuan Yang, Kai Zeng, Qingwang Wang, and Tao Shen. "Implicit Sharpness-Aware Minimization for Domain Generalization." Remote Sensing 16, no. 16 (2024): 2877. http://dx.doi.org/10.3390/rs16162877.

Full text

Abstract:

Domain generalization (DG) aims to learn knowledge from multiple related domains to achieve a robust generalization performance in unseen target domains, which is an effective approach to mitigate domain shift in remote sensing image classification. Although the sharpness-aware minimization (SAM) method enhances DG capability and improves remote sensing image classification performance by promoting the convergence of the loss minimum to a flatter loss surface, the perturbation loss (maximum loss within the neighborhood of a local minimum) of SAM fails to accurately measure the true sharpness o

APA, Harvard, Vancouver, ISO, and other styles

3

Wu, Tao, Tie Luo, and Donald C. Wunsch II. "CR-SAM: Curvature Regularized Sharpness-Aware Minimization." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 6 (2024): 6144–52. http://dx.doi.org/10.1609/aaai.v38i6.28431.

Full text

Abstract:

The capacity to generalize to future unseen data stands as one of the utmost crucial attributes of deep neural networks. Sharpness-Aware Minimization (SAM) aims to enhance the generalizability by minimizing worst-case loss using one-step gradient ascent as an approximation. However, as training progresses, the non-linearity of the loss landscape increases, rendering one-step gradient ascent less effective. On the other hand, multi-step gradient ascent will incur higher training cost. In this paper, we introduce a normalized Hessian trace to accurately measure the curvature of loss landscape on

APA, Harvard, Vancouver, ISO, and other styles

4

Xing, Xinda, Qiugang Zhan, Xiurui Xie, Yuning Yang, Qiang Wang, and Guisong Liu. "Flexible Sharpness-Aware Personalized Federated Learning." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 20 (2025): 21707–15. https://doi.org/10.1609/aaai.v39i20.35475.

Full text

Abstract:

Personalized federated learning (PFL) is a new paradigm to address the statistical heterogeneity problem in federated learning. Most existing PFL methods focus on leveraging global and local information such as model interpolation or parameter decoupling. However, these methods often overlook the generalization potential during local client learning. From a local optimization perspective, we propose a simple and general PFL method, Federated learning with Flexible Sharpness-Aware Minimization (FedFSA). Specifically, we emphasize the importance of applying a larger perturbation to critical laye

APA, Harvard, Vancouver, ISO, and other styles

5

Deng, Jiaxin, Junbiao Pang, Baochang Zhang, and Guodong Guo. "Asymptotic Unbiased Sample Sampling to Speed Up Sharpness-Aware Minimization." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 15 (2025): 16208–16. https://doi.org/10.1609/aaai.v39i15.33780.

Full text

Abstract:

Sharpness-Aware Minimization (SAM) has emerged as a promising approach for effectively reducing the generalization error. However, SAM incurs twice the computational cost compared to the base optimizer (e.g., SGD). We propose Asymptotic Unbiased data sampling to accelerate SAM (AUSAM), which maintains the model's generalization capacity while significantly enhancing computational efficiency. Concretely, we probabilistically sample a subset of data points beneficial for SAM optimization based on a theoretically guaranteed criterion, i.e., the Gradient Norm of each Sample (GNS). We further appro

APA, Harvard, Vancouver, ISO, and other styles

6

Zhou, Changbao, Jiawei Du, Ming Yan, Hengshan Yue, Xiaohui Wei, and Joey Tianyi Zhou. "SAR: Sharpness-Aware minimization for enhancing DNNs’ Robustness against bit-flip errors." Journal of Systems Architecture 156 (November 2024): 103284. http://dx.doi.org/10.1016/j.sysarc.2024.103284.

Full text

APA, Harvard, Vancouver, ISO, and other styles

7

Mariam, Iqra, Xiaorong Xue, and Kaleb Gadson. "A Retinal Vessel Segmentation Method Based on the Sharpness-Aware Minimization Model." Sensors 24, no. 13 (2024): 4267. http://dx.doi.org/10.3390/s24134267.

Full text

Abstract:

Retinal vessel segmentation is crucial for diagnosing and monitoring various eye diseases such as diabetic retinopathy, glaucoma, and hypertension. In this study, we examine how sharpness-aware minimization (SAM) can improve RF-UNet’s generalization performance. RF-UNet is a novel model for retinal vessel segmentation. We focused our experiments on the digital retinal images for vessel extraction (DRIVE) dataset, which is a benchmark for retinal vessel segmentation, and our test results show that adding SAM to the training procedure leads to notable improvements. Compared to the non-SAM model

APA, Harvard, Vancouver, ISO, and other styles

8

Liang, Hailun, Haowen Zheng, Hao Wang, Liu He, Haoyi Lin, and Yanyan Liang. "Exploring Flatter Loss Landscape Surface via Sharpness-Aware Minimization with Linear Mode Connectivity." Mathematics 13, no. 8 (2025): 1259. https://doi.org/10.3390/math13081259.

Full text

Abstract:

The Sharpness-Aware Minimization (SAM) optimizer connects flatness and generalization, suggesting that loss basins with lower sharpness are correlated with better generalization. However, SAM requires manually tuning the open ball radius, which complicates its practical application. To address this, we propose a method inspired by linear connectivity, using two models initialized differently as endpoints to automatically determine the optimal open ball radius. Specifically, we introduce distance regularization between the two models during training, which encourages them to approach each other

APA, Harvard, Vancouver, ISO, and other styles

9

Wei, Zheng, Xingjun Zhang, and Zhendong Tan. "Unifying and revisiting Sharpness-Aware Minimization with noise-injected micro-batch scheduler for efficiency improvement." Neural Networks 185 (May 2025): 107205. https://doi.org/10.1016/j.neunet.2025.107205.

Full text

APA, Harvard, Vancouver, ISO, and other styles

10

Jeong, In-Woong, Han-Jin Lee, Jae-Hwan Jeong, and Seok-Hwan Choi. "A Study on Malware Family Classification Method based on Separable Vision Transformer Using Sharpness-Aware Minimization." Journal of Korean Institute of Intelligent Systems 34, no. 4 (2024): 329–38. http://dx.doi.org/10.5391/jkiis.2024.34.4.329.

Full text

APA, Harvard, Vancouver, ISO, and other styles

11

Guo, Li, Weilong Chen, Yu Liao, Honghua Liao, and Jun Li. "An Edge-Preserved Image Denoising Algorithm Based on Local Adaptive Regularization." Journal of Sensors 2016 (2016): 1–6. http://dx.doi.org/10.1155/2016/2019569.

Full text

Abstract:

Image denoising methods are often based on the minimization of an appropriately defined energy function. Many gradient dependent energy functions, such as Potts model and total variation denoising, regard image as piecewise constant function. In these methods, some important information such as edge sharpness and location is well preserved, but some detailed image feature like texture is often compromised in the process of denoising. For this reason, an image denoising method based on local adaptive regularization is proposed in this paper, which can adaptively adjust denoising degree of noisy

APA, Harvard, Vancouver, ISO, and other styles

12

Han, Siyeon, Dat Ngo, Yeonggyu Choi, and Bongsoon Kang. "Autonomous Single-Image Dehazing: Enhancing Local Texture with Haze Density-Aware Image Blending." Remote Sensing 16, no. 19 (2024): 3641. http://dx.doi.org/10.3390/rs16193641.

Full text

Abstract:

Single-image dehazing is an ill-posed problem that has attracted a myriad of research efforts. However, virtually all methods proposed thus far assume that input images are already affected by haze. Little effort has been spent on autonomous single-image dehazing. Even though deep learning dehazing models, with their widely claimed attribute of generalizability, do not exhibit satisfactory performance on images with various haze conditions. In this paper, we present a novel approach for autonomous single-image dehazing. Our approach consists of four major steps: sharpness enhancement, adaptive

APA, Harvard, Vancouver, ISO, and other styles

13

Dung Nguyen, Duc, and Jae Wook Jeon. "Enhancing accuracy and sharpness of motion field with adaptive scheme and occlusion-aware filter." IET Image Processing 7, no. 2 (2013): 144–53. http://dx.doi.org/10.1049/iet-ipr.2012.0563.

Full text

APA, Harvard, Vancouver, ISO, and other styles

14

Bento, Nuno, Joana Rebelo, André V. Carreiro, François Ravache, and Marília Barandas. "Exploring Regularization Methods for Domain Generalization in Accelerometer-Based Human Activity Recognition." Sensors 23, no. 14 (2023): 6511. http://dx.doi.org/10.3390/s23146511.

Full text

Abstract:

The study of Domain Generalization (DG) has gained considerable momentum in the Machine Learning (ML) field. Human Activity Recognition (HAR) inherently encompasses diverse domains (e.g., users, devices, or datasets), rendering it an ideal testbed for exploring Domain Generalization. Building upon recent work, this paper investigates the application of regularization methods to bridge the generalization gap between traditional models based on handcrafted features and deep neural networks. We apply various regularizers, including sparse training, Mixup, Distributionally Robust Optimization (DRO

APA, Harvard, Vancouver, ISO, and other styles

15

Raj, Anish, Fabian Tollens, Laura Hansen, et al. "Deep Learning-Based Total Kidney Volume Segmentation in Autosomal Dominant Polycystic Kidney Disease Using Attention, Cosine Loss, and Sharpness Aware Minimization." Diagnostics 12, no. 5 (2022): 1159. http://dx.doi.org/10.3390/diagnostics12051159.

Full text

Abstract:

Early detection of the autosomal dominant polycystic kidney disease (ADPKD) is crucial as it is one of the most common causes of end-stage renal disease (ESRD) and kidney failure. The total kidney volume (TKV) can be used as a biomarker to quantify disease progression. The TKV calculation requires accurate delineation of kidney volumes, which is usually performed manually by an expert physician. However, this is time-consuming and automated segmentation is warranted. Furthermore, the scarcity of large annotated datasets hinders the development of deep learning solutions. In this work, we addre

APA, Harvard, Vancouver, ISO, and other styles

16

Vishal, Puri, and Ramesh Babu A. "Deployment of Context-Aware Sensor in Wireless Sensor Network Based on the Variants of Genetic Algorithm." International Journal of Artificial Life Research 8, no. 2 (2018): 1–24. http://dx.doi.org/10.4018/ijalr.2018070101.

Full text

Abstract:

Wireless sensor networks (WSNs) are generally a group of spatially scattered and devoted sensors to record and monitor the physical environmental condition, and the collected data is grouped at a central location. In fact, the environmental conditions such as sound, humidity, temperature, wind, pollution levels, etc., can be clearly determined by WSNs. The principal objective of WSNs is to organize the whole sensor nodes in their related positions, thereby developing an effective network. In WSNs, target COVerage (TCOV) and Network CONnectivity (NCON) are the main concern of the sensor deploym

APA, Harvard, Vancouver, ISO, and other styles

17

Chen, Hui, Charles Gouin-Vallerand, Kévin Bouchard, et al. "Enhancing Human Activity Recognition in Smart Homes with Self-Supervised Learning and Self-Attention." Sensors 24, no. 3 (2024): 884. http://dx.doi.org/10.3390/s24030884.

Full text

Abstract:

Deep learning models have gained prominence in human activity recognition using ambient sensors, particularly for telemonitoring older adults’ daily activities in real-world scenarios. However, collecting large volumes of annotated sensor data presents a formidable challenge, given the time-consuming and costly nature of traditional manual annotation methods, especially for extensive projects. In response to this challenge, we propose a novel AttCLHAR model rooted in the self-supervised learning framework SimCLR and augmented with a self-attention mechanism. This model is designed for human ac

APA, Harvard, Vancouver, ISO, and other styles

18

Takyu, Osamu, Keita Takeda, Ryuji Miyamoto, Koichi Adachi, Mai Ohta, and Takeo Fujii. "An Environment-Aware Adaptive Data-Gathering Method for Packet-Level Index Modulation in LPWA." Sensors 24, no. 8 (2024): 2514. http://dx.doi.org/10.3390/s24082514.

Full text

Abstract:

Low-power wide-area (LPWA) is a communication technology for the IoT that allows low power consumption and long-range communication. Additionally, packet-level index modulation (PLIM) can transmit additional information using multiple frequency channels and time slots. However, in a competitive radio access environment, where multiple sensors autonomously determine packet transmission, packet collisions occur when transmitting the same information. The packet collisions cause a reduction in the throughput. A method has been proposed to design a mapping table that shows the correspondence betwe

APA, Harvard, Vancouver, ISO, and other styles

19

Zhu, Huichao, Yu Wu, Ge Yang, Ruijie Song, Jun Yu, and Jianwei Zhang. "Electronic Nose Drift Suppression Based on Smooth Conditional Domain Adversarial Networks." Sensors 24, no. 4 (2024): 1319. http://dx.doi.org/10.3390/s24041319.

Full text

Abstract:

Anti-drift is a new and serious challenge in the field related to gas sensors. Gas sensor drift causes the probability distribution of the measured data to be inconsistent with the probability distribution of the calibrated data, which leads to the failure of the original classification algorithm. In order to make the probability distributions of the drifted data and the regular data consistent, we introduce the Conditional Adversarial Domain Adaptation Network (CDAN)+ Sharpness Aware Minimization (SAM) optimizer—a state-of-the-art deep transfer learning method.The core approach involves the c

APA, Harvard, Vancouver, ISO, and other styles

20

AbdulAlim, Md Abdul, Yu Cheng Wu, and Wei Wang. "A Fuzzy Based Clustering Protocol for Energy-Efficient Wireless Sensor Networks." Advanced Materials Research 760-762 (September 2013): 685–90. http://dx.doi.org/10.4028/www.scientific.net/amr.760-762.685.

Full text

Abstract:

Minimization of energy consumption is one of the most important research areas in Wireless Sensor Networks. Nowadays, the paradigms of computational intelligence (CI) are widely used in WSN, such as localization, clustering, energy aware routing, task scheduling, security, etc. Though many fuzzy based clustering techniques have been proposed earlier, many of them could not increase the total network life time in terms of LND (Last Node Dies) with comparing to LEACH. In this paper, a fuzzy logic based energy-aware dynamic clustering technique is proposed, which increases the network lifetime in

APA, Harvard, Vancouver, ISO, and other styles

21

Garg, Anchal, and Gurjinder Kaur. "Zone Head Selection Algorithm Based on Fuzzy Logic for Wireless Sensor Networks." Journal of University of Shanghai for Science and Technology 23, no. 10 (2021): 29–37. http://dx.doi.org/10.51201/jusst/21/09706.

Full text

Abstract:

Clustering extends energy resources, improves scalability and preserves communication bandwidth of the network. Clustering is either categorized as static and dynamic or as equal and unequal. Hot-spots issue needs a high overhead and is prone to connectivity problems in the wireless sensor network and this can be only possible because of unequal clustering. In this paper a zone divisional method based on fuzzy logic has been proposed. This method uses a fuzzy logic to form clusters and allot nodes to them for the reduction of energy consumption, and extends the age of the sensor network. The s

APA, Harvard, Vancouver, ISO, and other styles

22

Bruschi, Roberto, Alessandro Carrega, and Franco Davoli. "A Game for Energy-Aware Allocation of Virtualized Network Functions." Journal of Electrical and Computer Engineering 2016 (2016): 1–10. http://dx.doi.org/10.1155/2016/4067186.

Full text

Abstract:

Network Functions Virtualization (NFV) is a network architecture concept where network functionality is virtualized and separated into multiple building blocks that may connect or be chained together to implement the required services. The main advantages consist of an increase in network flexibility and scalability. Indeed, each part of the service chain can be allocated and reallocated at runtime depending on demand. In this paper, we present and evaluate an energy-aware Game-Theory-based solution for resource allocation of Virtualized Network Functions (VNFs) within NFV environments. We con

APA, Harvard, Vancouver, ISO, and other styles

23

Belliardo, Federico, Fabio Zoratti, Florian Marquardt, and Vittorio Giovannetti. "Model-aware reinforcement learning for high-performance Bayesian experimental design in quantum metrology." Quantum 8 (December 10, 2024): 1555. https://doi.org/10.22331/q-2024-12-10-1555.

Full text

Abstract:

Quantum sensors offer control flexibility during estimation by allowing manipulation by the experimenter across various parameters. For each sensing platform, pinpointing the optimal controls to enhance the sensor&apos;s precision remains a challenging task. While an analytical solution might be out of reach, machine learning offers a promising avenue for many systems of interest, especially given the capabilities of contemporary hardware. We have introduced a versatile procedure capable of optimizing a wide range of problems in quantum metrology, estimation, and hypothesis testing by comb

APA, Harvard, Vancouver, ISO, and other styles

24

Liu, Daixian, Bingli Wang, Linhui Peng, Han Wang, Yijuan Wang, and Yonghao Pan. "HSDNet: a poultry farming model based on few-shot semantic segmentation addressing non-smooth and unbalanced convergence." PeerJ Computer Science 10 (June 7, 2024): e2080. http://dx.doi.org/10.7717/peerj-cs.2080.

Full text

Abstract:

Poultry farming is an indispensable part of global agriculture, playing a crucial role in food safety and economic development. Managing and preventing diseases is a vital task in the poultry industry, where semantic segmentation technology can significantly enhance the efficiency of traditional manual monitoring methods. Furthermore, traditional semantic segmentation has achieved excellent results on extensively manually annotated datasets, facilitating real-time monitoring of poultry. Nonetheless, the model encounters limitations when exposed to new environments, diverse breeding varieties,

APA, Harvard, Vancouver, ISO, and other styles

25

Lyu, Xingyu, Qianqian Xu, Zhiyong Yang, Shaojie Lyu, and Qingming Huang. "SSE-SAM: Balancing Head and Tail Classes Gradually Through Stage-Wise SAM." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 18 (2025): 19278–86. https://doi.org/10.1609/aaai.v39i18.34122.

Full text

Abstract:

Real-world datasets often exhibit a long-tailed distribution, where vast majority of classes known as tail classes have only few samples. Traditional methods tend to overfit on these tail classes. Recently, a new approach called Imbalanced SAM (ImbSAM) is proposed to leverage the generalization benefits of Sharpness-Aware Minimization (SAM) for long-tailed distributions. The main strategy is to merely enhance the smoothness of the loss function for tail classes. However, we argue that improving generalization in long-tail scenarios requires a careful balance between head and tail classes. We s

APA, Harvard, Vancouver, ISO, and other styles

26

Patil, Geeta, and Arvind Mallikarjun Bhavikatti. "Energy aware optimized dynamic routing mechanism in wireless sensor networks." Indonesian Journal of Electrical Engineering and Computer Science 30, no. 2 (2023): 944. http://dx.doi.org/10.11591/ijeecs.v30.i2.pp944-955.

Full text

Abstract:

A trade-off between energy efficiency and optimized routing is massively recommended for transmission efficiency enhancement in wireless sensor networks (WSNs). Therefore, in this paper, graph-based energy optimized dynamic routing (GEODR) mechanism is introduced to set up a balance between energy consumption minimization and throughput enhancement using a dynamic and optimized routing mechanism in WSNs. A clustering scheme is employed based on graph theory, and cluster boundaries are formed using distance vectors. Cluster head (CH) selection is performed based on residual energy, the distance

APA, Harvard, Vancouver, ISO, and other styles

27

Geeta, Patil, and Mallikarjun Bhavikatti Arvind. "Energy aware optimized dynamic routing mechanism in wireless sensor networks." Energy aware optimized dynamic routing mechanism in wireless sensor networks 30, no. 2 (2023): 944–55. https://doi.org/10.11591/ijeecs.v30.i2.pp944-955.

Full text

Abstract:

A trade-off between energy efficiency and optimized routing is massively recommended for transmission efficiency enhancement in wireless sensor networks (WSNs). Therefore, in this paper, graph-based energy optimized dynamic routing (GEODR) mechanism is introduced to set up a balance between energy consumption minimization and throughput enhancement using a dynamic and optimized routing mechanism in WSNs. A clustering scheme is employed based on graph theory, and cluster boundaries are formed using distance vectors. Cluster head (CH) selection is performed based on residual energy, the distance

APA, Harvard, Vancouver, ISO, and other styles

28

Garg, Anchal, and Gurjinder Kaur. "Fuzzy Logic Based Zone Head Selection Algorithm for Wireless Sensor Networks." Journal of University of Shanghai for Science and Technology 23, no. 07 (2021): 1210–15. http://dx.doi.org/10.51201/jusst/21/07294.

Full text

Abstract:

Hot-spots are a problem that comes in the cluster-based routing protocol that employs multi-hop communication due to this problem the energy among the sensor nodes is not balanced. The hot-spots issue requires high overhead and is prone to connectivity issues in the sensor network this can be only possible because of unequal clustering. In this method, we have to act on all the nodes of the sensor network for communication. This process consumes high system energy if the numbers of nodes are very high. To offer guaranteed connectivity, decrease high usage and complexity, a fuzzy logic-based zo

APA, Harvard, Vancouver, ISO, and other styles

29

Mangesh Pujari, Anil Kumar Pakina, and Anshul Goel. "Balancing Innovation and Privacy: A Red Teaming Approach to Evaluating Phone-Based Large Language Models under AI Privacy Regulations." International Journal Science and Technology 2, no. 3 (2023): 117–27. https://doi.org/10.56127/ijst.v2i3.1956.

Full text

Abstract:

The rapid deployment of large language models (LLMs) on mobile devices has introduced significant privacy concerns, particularly regarding data collection, user profiling, and compliance with evolving AI regulations such as the GDPR and the AI Act. While these on-device LLMs promise improved latency and user experience, their potential to inadvertently leak sensitive information remains understudied. This paper proposes a red teaming framework to systematically assess the privacy risks of phone-based LLMs, simulating adversarial attacks to identify vulnerabilities in model behavior, data stora

APA, Harvard, Vancouver, ISO, and other styles

30

R. N. Sandhiya. "Adaptive Load-Balanced Clustering for Enhanced Energy Efficiency and Fault Tolerance in Wireless Sensor Networks." Journal of Information Systems Engineering and Management 10, no. 35s (2025): 1177–91. https://doi.org/10.52783/jisem.v10i35s.6288.

Full text

Abstract:

Wireless Sensor Networks (WSNs) are critical in distributed monitoring systems, where optimal performance relies on efficient energy usage, balanced data handling, and fault resilience. Traditional clustering protocols, such as Energy-Aware Hybrid Clustering (EAHC), primarily focus on energy metrics but often neglect real-time load balancing and adaptive reconfiguration. This leads to node failures, uneven energy depletion, and increased latency. Clustering methods lacking dynamic adaptation to node load and failure conditions often face performance degradation due to hotspot formation, unbala

APA, Harvard, Vancouver, ISO, and other styles

31

Wu, Xintong, Shanlin Sun, Yun Li, Zhicheng Tan, Wentao Huang, and Xing Yao. "A Power Control Algorithm Based on Outage Probability Awareness in Vehicular Ad Hoc Networks." Advances in Multimedia 2018 (August 1, 2018): 1–8. http://dx.doi.org/10.1155/2018/8729645.

Full text

Abstract:

This paper addresses the problem of adaptive power control based on outage probability minimization in Vehicular Ad Hoc Networks (VANETs), called a Power Control Algorithm Based on Outage Probability Awareness (PC-OPA). Unlike most of the existing works, our power control method aims at minimizing the outage probability and then is subject to the density of nodes in certain area. To fulfill power control, cumulative interference is assumed to be available at the transmitter of each terminal. The transmitters sent data by maximum power and then get the cumulative interference-aware outage proba

APA, Harvard, Vancouver, ISO, and other styles

32

Mueen, Ahmed, Mohammad Awedh, and Bassam Zafar. "Multi-obstacle aware smart navigation system for visually impaired people in fog connected IoT-cloud environment." Health Informatics Journal 28, no. 3 (2022): 146045822211126. http://dx.doi.org/10.1177/14604582221112609.

Full text

Abstract:

Design of smart navigation for visually impaired/blind people is a hindering task. Existing researchers analyzed it in either indoor or outdoor environment and also it’s failed to focus on optimum route selection, latency minimization and multi-obstacle presence. In order to overcome these challenges and to provide precise assistance to visually impaired people, this paper proposes smart navigation system for visually impaired people based on both image and sensor outputs of the smart wearable. The proposed approach involves the upcoming processes: (i) the input query of the visually impaired

APA, Harvard, Vancouver, ISO, and other styles

33

Luo, Fan-Ming, Shengyi Jiang, Yang Yu, ZongZhang Zhang, and Yi-Feng Zhang. "Adapt to Environment Sudden Changes by Learning a Context Sensitive Policy." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 7 (2022): 7637–46. http://dx.doi.org/10.1609/aaai.v36i7.20730.

Full text

Abstract:

Dealing with real-world reinforcement learning (RL) tasks, we shall be aware that the environment may have sudden changes. We expect that a robust policy is able to handle such changes and adapt to the new environment rapidly. Context-based meta reinforcement learning aims at learning environment adaptable policies. These methods adopt a context encoder to perceive the environment on-the-fly, following which a contextual policy makes environment adaptive decisions according to the context. However, previous methods show lagged and unstable context extraction, which are hard to handle sudden ch

APA, Harvard, Vancouver, ISO, and other styles

34

Anjum, Usman, Chris Stockman, Cat Luong, and Felix Zhan. "Using adaptive learning and momentum to improve generalization." Neural Computing and Applications, May 10, 2025. https://doi.org/10.1007/s00521-025-11220-7.

Full text

Abstract:

Abstract In this paper, we propose a novel algorithm called adaptive learning & momentum sharpness-aware minimization MAML (AS-MAML) that builds upon the concept of sharpness-aware minimization and adaptive learning and momentum to improve generalization. We prove theoretically by performing convergence analysis and PAC-Bayes analysis that AS-MAML performs better than the state-of-the-art algorithms in model-agnostic meta-learning. We draw the same conclusion through extensive experimental analysis using benchmark datasets.

APA, Harvard, Vancouver, ISO, and other styles

35

Xie, Tianci, Tao Li, and Ruoxue Wu. "Adaptive Sharpness-Aware Minimization for Adversarial Domain Generalization." IEEE Transactions on Computational Social Systems, 2024, 1–8. http://dx.doi.org/10.1109/tcss.2024.3388894.

Full text

APA, Harvard, Vancouver, ISO, and other styles

36

Zhang, Xiongtao, Ji Wang, Weidong Bao, Wenhua Xiao, Yaohong Zhang, and Lihua Liu. "Self-adaptive asynchronous federated optimizer with adversarial sharpness-aware minimization." Future Generation Computer Systems, July 2024. http://dx.doi.org/10.1016/j.future.2024.07.045.

Full text

APA, Harvard, Vancouver, ISO, and other styles

37

Sun, Hao, Li Shen, Qihuang Zhong, et al. "AdaSAM: Boosting sharpness-aware minimization with adaptive learning rate and momentum for training deep neural networks." Neural Networks, November 2023. http://dx.doi.org/10.1016/j.neunet.2023.10.044.

Full text

APA, Harvard, Vancouver, ISO, and other styles

38

Chen, Simiao, Xiaoge Deng, Dongpo Xu, Tao Sun, and Dongsheng Li. "Decentralized stochastic sharpness-aware minimization algorithm." Neural Networks, April 2024, 106325. http://dx.doi.org/10.1016/j.neunet.2024.106325.

Full text

APA, Harvard, Vancouver, ISO, and other styles

39

Huang, Bin, Ying Xie, and Chaoyang Xu. "Learning with noisy labels via clean aware sharpness aware minimization." Scientific Reports 15, no. 1 (2025). https://doi.org/10.1038/s41598-025-85679-8.

Full text

APA, Harvard, Vancouver, ISO, and other styles

40

Su, Dan, Long Jin, and Jun Wang. "Noise-resistant sharpness-aware minimization in deep learning." Neural Networks, October 2024, 106829. http://dx.doi.org/10.1016/j.neunet.2024.106829.

Full text

APA, Harvard, Vancouver, ISO, and other styles

41

Liu, Ren, Fengmiao Bian, and Xiaoqun Zhang. "Binary Quantized Network Training With Sharpness-Aware Minimization." Journal of Scientific Computing 94, no. 1 (2022). http://dx.doi.org/10.1007/s10915-022-02064-7.

Full text

APA, Harvard, Vancouver, ISO, and other styles

42

Dai, Rong, Xun Yang, Yan Sun, et al. "FedGAMMA: Federated Learning With Global Sharpness-Aware Minimization." IEEE Transactions on Neural Networks and Learning Systems, 2023, 1–14. http://dx.doi.org/10.1109/tnnls.2023.3304453.

Full text

APA, Harvard, Vancouver, ISO, and other styles

43

Liu, Liangchen, Nannan Wang, Dawei Zhou, et al. "Generalizable Prompt Learning via Gradient Constrained Sharpness-aware Minimization." IEEE Transactions on Multimedia, 2024, 1–14. https://doi.org/10.1109/tmm.2024.3521702.

Full text

APA, Harvard, Vancouver, ISO, and other styles

44

Park, Jinseong, Hoki Kim, Yujin Choi, Woojin Lee, and Jaewook Lee. "Fast Sharpness-Aware Minimization for Time Series Classification and Forecasting." SSRN Electronic Journal, 2023. http://dx.doi.org/10.2139/ssrn.4346500.

Full text

APA, Harvard, Vancouver, ISO, and other styles

45

Abedini, Fereshteh, and Sasan Gooran. "Structure-Aware Color Halftoning with Adaptive Sharpness Control." Journal of Imaging Science and Technology 66, no. 6 (2022). https://doi.org/10.2352/J.ImagingSci.Technol.2022.66.6.060404.

Full text

Abstract:

Structure-aware halftoning algorithms aim at improving their non-structure-aware version by preserving high-frequency details, structures, and tones and by employing additional information from the input image content. The recently proposed achromatic structure-aware Iterative Method Controlling the Dot Placement (IMCDP) halftoning algorithm uses the angle of the dominant line in each pixel’s neighborhood as supplementary information to align halftone structures with the dominant orientation in each region and results in sharper halftones, gives a

APA, Harvard, Vancouver, ISO, and other styles

46

Kang, Helei, Yiming Jiang, Jinlan Liu, and Dongpo Xu. "Sharpness-Aware Minimization method with momentum acceleration for deep neural networks." Knowledge-Based Systems, July 2025, 113967. https://doi.org/10.1016/j.knosys.2025.113967.

Full text

APA, Harvard, Vancouver, ISO, and other styles

47

Abedini, Fereshteh, and Sasan Gooran. "Structure-Aware Color Halftoning with Adaptive Sharpness Control." Journal of Imaging Science and Technology, November 1, 2022, 060405–1. http://dx.doi.org/10.2352/j.imagingsci.technol.2022.66.6.060405.

Full text

APA, Harvard, Vancouver, ISO, and other styles

48

Rostand, Jules, Chen-Chien James Hsu, and Cheng-Kai Lu. "Comprehensive survey on the effectiveness of sharpness aware minimization and its progressive variants." Journal of the Chinese Institute of Engineers, August 4, 2024, 1–9. http://dx.doi.org/10.1080/02533839.2024.2383592.

Full text

APA, Harvard, Vancouver, ISO, and other styles

49

Xu, Zhengguo, Hengtuo Pan, Wei Ye, Zhuangwei Xu, and Hongkai Wang. "Detection Method of Wheat Rust Based on Transfer Learning and Sharpness‐Aware Minimization." Plant Pathology, October 24, 2022. http://dx.doi.org/10.1111/ppa.13661.

Full text

APA, Harvard, Vancouver, ISO, and other styles

50

Wu, Qingtao, Yong Zhang, Muhua Liu, Junlong Zhu, Ruijuan Zheng, and Mingchuan Zhang. "Federated Model-Agnostic Meta-Learning With Sharpness-Aware Minimization for Internet of Things Optimization." IEEE Internet of Things Journal, 2024, 1. http://dx.doi.org/10.1109/jiot.2024.3417295.

Full text

APA, Harvard, Vancouver, ISO, and other styles

We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!