We present an automated data augmentation approach for image classification. The problem is formulated as a Monte Carlo sampling problem where the goal is to approximate the optimal augmentation policies using a polic...
详细信息
We present an automated data augmentation approach for image classification. The problem is formulated as a Monte Carlo sampling problem where the goal is to approximate the optimal augmentation policies using a policy mixture distribution. We propose a particle filter scheme for the policy search where the probability of applying a set of augmentation operations forms the state of the filter. The policy performance is measured based on the loss function difference between a reference model and the actual model. This performance measure is then used to re-weight the particles and finally update the policy distribution. In our experiments, we show that our formulation for automated augmentation reaches promising results on CIFAR-10, CIFAR-100, and ImageNet datasets using the standard network architectures for this problem. By comparing with the related work, our method reaches a balance between the computational cost of policy search and the model performance. The source code of our approach is publicly available.
Ensuring precise train localization is crucial for the operational safety and efficiency of railway networks. Conventional localization techniques face limitations due to dynamic environmental noise, impacting the acc...
详细信息
ISBN:
(数字)9789887581581
ISBN:
(纸本)9798350366907
Ensuring precise train localization is crucial for the operational safety and efficiency of railway networks. Conventional localization techniques face limitations due to dynamic environmental noise, impacting the accuracy of such systems. In response, this study proposes a sophisticated approach that incorporates a deeplearning-enhanced Invariant Extended Kalman Filter, utilizing a Convolutional Neural Network-Long Short-Term Memory(CNN-LSTM) architecture. This innovative method dynamically adjusts the noise parameters within the Kalman filtering process. The CNN component extracts spatial features,while the LSTM module analyzes temporal sequences, thereby optimizing the filter's performance under varying environmental conditions. The integration of Global Navigation Satellite System(GNSS) and Inertial Navigation System(INS) data forms the core of our investigation, addressing the complexities inherent in train localization tasks. Rigorous evaluations on real-world datasets have demonstrated a notable enhancement in localization accuracy, achieving a [specific improvement percentage] over conventional Kalman filter methods. The outcomes of this research underscore the transformative impact of deeplearning on railway system advancements and set a foundation for subsequent innovations in intelligent transportation systems. By merging advanced deeplearning algorithms with traditional signal processing, our work contributes to the evolution of more dependable and efficient train localization solutions, paving the way for future developments in this critical area of intelligent transportation systems.
Stochastic gradient descent (SGD) augmented with various momentum variants (e.g. heavy ball momentum (SHB) and Nesterov's accelerated gradient (NAG)) has been the default optimizer for many learning tasks. Tuning ...
详细信息
ISBN:
(纸本)9781450383325
Stochastic gradient descent (SGD) augmented with various momentum variants (e.g. heavy ball momentum (SHB) and Nesterov's accelerated gradient (NAG)) has been the default optimizer for many learning tasks. Tuning the optimizer's hyperparameters is arguably the most time-consuming part of model training. Many new momentum variants, despite their empirical advantage over classical SHB/NAG, introduce even more hyperparameters to tune. Automating the tedious and error-prone tuning is essential for AutoML. This paper focuses on how to efficiently tune a large class of multistage momentum variants to improve generalization. We use the general formulation of quasi-hyperbolic momentum (QHM) and extend "constant and drop", the widespread learning rate.. scheduler where.. is set large initially and then dropped every few epochs, to other hyperparameters (e.g. batch size.., momentum parameter beta, instant discount factor nu). Multistage QHM is a unified framework which covers a large family of momentum variants as its special cases (e.g. vanilla SGD/SHB/NAG). Existing works mainly focus on scheduling..'s decay, while multistage QHM allows additional varying hyperparameters such as b, beta, and nu, and demonstrates better generalization ability than only tuning alpha. Our tuning strategies have rigorous justifications rather than a blind trial-and-error. We theoretically prove why our tuning strategies could improve generalization. We also show the convergence of multistage QHM for general nonconvex objective functions. Our strategies simplify the tuning process and beat competitive optimizers in test accuracy empirically.
Driven by the visions of Internet of Things and 5G communications, the edge computing systems integrate computing, storage, and network resources at the edge of the network to provide computing infrastructure, enablin...
详细信息
Driven by the visions of Internet of Things and 5G communications, the edge computing systems integrate computing, storage, and network resources at the edge of the network to provide computing infrastructure, enabling developers to quickly develop and deploy edge applications. At present, the edge computing systems have received widespread attention in both industry and academia. To explore new research opportunities and assist users in selecting suitable edge computing systems for specific applications, this survey paper provides a comprehensive overview of the existing edge computing systems and introduces representative projects. A comparison of open-source tools is presented according to their applicability. Finally, we highlight energy efficiency and deep learning optimization of edge computing systems. Open issues for analyzing and designing an edge computing system are also studied in this paper.
The proliferation of mobile devices is producing a new wave of mobile visual search applications that enable users to sense their surroundings with smart phones. As the particular challenges of mobile visual search, a...
详细信息
The proliferation of mobile devices is producing a new wave of mobile visual search applications that enable users to sense their surroundings with smart phones. As the particular challenges of mobile visual search, achieving high recognition bitrate becomes the consistent target of existed related works. In this paper, we explore to holistically exploit the deeplearning-based hashing methods for more robust and instant mobile visual search. Firstly, we present a comprehensive survey of the existed deeplearning based hashing methods, which showcases their remarkable power of automatic learning highly robust and compact binary code representation for visual search. Furthermore, in order to implement the deeplearning hashing on computation and memory constrained mobile device, we investigate the deep learning optimization works to accelerate the computation and reduce the model size. Finally, we demonstrate a case study of deeplearning hashing based mobile visual search system. The evaluations show that the proposed system can significantly improve 70% accuracy in MAP than traditional methods, and only needs less than one second computation time on the ordinary mobile phone. Finally, with the comprehensive study, we discuss the open issues and future research directions of deeplearning hashing for mobile visual search.
暂无评论