Recent developments in the filed of Deep Learning have demonstrated that Deep Neural Networks(DNNs) are vulnerable to adversarial examples. Specifically, in image classification, an adversarial example can fool the well trained deep neural networks by adding barely imperceptible perturbations to clean images. Adversarial Training, one of the most direct and effective methods, minimizes the losses of perturbed-data to learn robust deep networks against adversarial attacks. It has been proven that using the fast gradient sign method (FGSM) can achieve Fast Adversarial Training. However, FGSM-based adversarial training may finally obtain a failed model because of overfitting to FGSM samples. In this paper, we proposed the Diversified Initialized Perturbations Adversarial Training (DIP-FAT) which involves seeking the initialization of the perturbation via enlarging the output distances of the target model in a random directions. Due to the diversity of random directions, the embedded fast adversarial training using FGSM increases the information from the adversary and reduces the possibility of overfitting. In addition to preventing overfitting, the extensive results show that our proposed DIP-FAT technique can also improve the accuracy of the clean data. The biggest advantage of DIP-FAT method: achieving the best banlance among clean-data, perturbed-data and efficiency.
With the rapid development of neural network, significant breakthroughs have been made in many aspects of object detection which has been widely used in many fields such as intelligent transportation and industrial detection. The State Grid is also focusing on object detection and related technologies to advance the intelligence of China's power grid in operations and maintenance and other fields. Therefore, in this paper we propose a fire detection oriented in server room. Since edge computing ensures responsiveness and reduces server load, object detection is better suited for deployment under edge computing. However, embedded devices in edge computing often have significant limitations in terms of storage and energy consumption. Traditional object detection algorithms are implemented by neural networks, which require large computational and storage resources, which conflict with edge computing. Therefore, we implement lightweight fire detection algorithms for edge computing via MobileNet to reduce parameter size and increase speed, and enhance multi-scale detection capabilities with the YOLOF algorithm.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.