The scheduling of parallel tasks is a topic that has received a lot of attention in recent years, in particular, due to the development of larger HPC clusters. It is regarded as an interesting problem because when combined with performant hardware, it ensures fast and efficient computing. However, it comes with a cost. The growing number of HPC clusters entails a greater global energy consumption which has a clear negative environmental impact. A green solution is thus required to find a compromise between energy-saving and high-performance computing within those clusters. In this paper, we evaluate the use of malleable jobs and idle servers powering off as a way to reduce both jobs mean stretch time and servers average power consumption. Malleable jobs have the particularity that the number of allocated servers can be changed during runtime. We present an energy-aware greedy algorithm with Particle Swarm Optimized parameters as a possible solution to schedule malleable jobs. An in-depth evaluation of the approach is then outlined using results from a simulator that was developed to handle malleable jobs. The results show that the use of malleable tasks can lead to an improved performance in terms of power consumption. We believe that our results open the door for further investigations on using malleable jobs models coupled with the energy-saving aspect.
In the past years, RGB-based deepfake detection has shown notable progress thanks to the development of effective deep neural networks. However, the performance of deepfake detectors remains primarily dependent on the quality of the forged content and the level of artifacts introduced by the forgery method. To detect these artifacts, it is often necessary to separate and analyze the frequency components of an image. In this context, we propose to utilize the high-frequency components of color images by introducing an end-to-end trainable module that (a) extracts features from high-frequency components and (b) fuses them with the features of the RGB input. The module not only exploits the high-frequency anomalies present in manipulated images but also can be used with most RGB-based deepfake detectors. Experimental results show that the proposed approach boosts the performance of state-of-the-art networks, such as XceptionNet and EfficientNet, on a challenging deepfake dataset. I. INTRODUCTIONDeepfakes are images and videos that seem genuine to the human eyes, whereas, in reality, they are either entirely or partially generated by an artificial intelligence algorithm. Deepfakes appeared in 2017 as adult forged content, depicting faces that were swapped with celebrities' faces [1]. As a technology, deepfakes have creative applications in movie post-production, dubbing, productive education, and identity anonymization. Nevertheless, they remain a significant threat to the public order and international peace 1 , especially with the virality of social media 2 .Consequently, developing automated deepfake detection tools has become a pressing matter. Deepfake detection started growing alongside the development of deepfake generation methods and open-source software like Face-Swap 3 , FakeApp 4 and DeepFaceLab [6]. Researchers started building image and video databases of fake content, focusing on key properties, such as visual quality, level of artifacts, and setup diversity. Most of deepfake detectors operate on RGB data, as it is the most abundant form [5]. These detectors can be artifact-specific or undirected [7]. In the first case, they try to find particular anomalies produced by the deepfake generation methods. Such irregularities can manifest as inconsistencies in the noise level, the color, the 1 https://www.theguardian.com/world/2021/apr/22/ european-mps-targeted-by-deepfake-video-calls-imitating-russian-opposition 2 https://www.bbc.com/news/technology-49961089 3 https:
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with đź’™ for researchers
Part of the Research Solutions Family.