Cachier: Edge-Caching for Recognition Applications

Drolia, Utsav; Guo, Katherine; Tan, Jiaqi; Gandhi, Rajeev; Narasimhan, Priya

doi:10.1109/icdcs.2017.94

Cited by 131 publications

(70 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…4.13.6 Image and Face Recognition. The authors of [271] focus on image recognition based mobile applications that are latency sensitive and are soft real-time in nature. They present the idea of using an edge server as a cache with computing resources.…”

Section: 134mentioning

confidence: 99%

All one needs to know about fog computing and related edge computing paradigms: A complete survey

Yousefpour

Fung

Nguyen

et al. 2019

Journal of Systems Architecture

1,111

613

View full text Add to dashboard Cite

With the Internet of Things (IoT) becoming part of our daily life and our environment, we expect rapid growth in the number of connected devices. IoT is expected to connect billions of devices and humans to bring promising advantages for us. With this growth, fog computing, along with its related edge computing paradigms, such as multi-access edge computing (MEC) and cloudlet, are seen as promising solutions for handling the large volume of securitycritical and time-sensitive data that is being produced by the IoT. In this paper, we first provide a tutorial on fog computing and its related computing paradigms, including their similarities and differences. Next, we provide a taxonomy of research topics in fog computing, and through a comprehensive survey, we summarize and categorize the efforts on fog computing and its related computing paradigms. Finally, we provide challenges and future directions for research in fog computing.

show abstract

Section: 134mentioning

confidence: 99%

All one needs to know about fog computing and related edge computing paradigms: A complete survey

Yousefpour

Fung

Nguyen

et al. 2019

Journal of Systems Architecture

1,111

613

View full text Add to dashboard Cite

show abstract

“…But caching results locally does not scale beyond tens of images, then Cachier [93] is proposed to achieve recognition of thousands of objects. In Cachier, results of edge intelligence application are cached in the edge server, storing the features of input (e.g., image) and the corresponding task results.…”

Section: Resultsmentioning

confidence: 99%

Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing

et al. 2019

View full text Add to dashboard Cite

With the breakthroughs in deep learning, the recent years have witnessed a booming of artificial intelligence (AI) applications and services, spanning from personal assistant to recommendation systems to video/audio surveillance. More recently, with the proliferation of mobile computing and Internet-of-Things (IoT), billions of mobile and IoT devices are connected to the Internet, generating zillions Bytes of data at the network edge. Driving by this trend, there is an urgent need to push the AI frontiers to the network edge so as to fully unleash the potential of the edge big data. To meet this demand, edge computing, an emerging paradigm that pushes computing tasks and services from the network core to the network edge, has been widely recognized as a promising solution.The resulted new inter-discipline, edge AI or edge intelligence, is beginning to receive a tremendous amount of interest. However, research on edge intelligence is still in its infancy stage, and a dedicated venue for exchanging the recent advances of edge intelligence is highly desired by both the computer system and artificial intelligence communities. To this end, we conduct a comprehensive survey of the recent research efforts on edge intelligence. Specifically, we first review the background and motivation for artificial intelligence running at the network edge. We then provide an overview of the overarching architectures, frameworks and emerging key technologies for deep learning model towards training/inference at the network edge. Finally, we discuss future research opportunities on edge intelligence. We believe that this survey will elicit escalating attentions, stimulate fruitful discussions and inspire further research ideas on edge intelligence.

show abstract

“…Once the feature descriptors are extracted, the images can be classified by matching the features through existing models that are already trained with features extracted from a database of images. This step involves using different algorithms, such as nearest neighbor matching or machine learning models [155]. The final results from object recognition can be transferred to the cloud or UEs.…”

Section: B Video Analysis Pipelines At the Edgementioning

confidence: 99%

“…The latency of the task placement is overall lower than other baseline approaches with minimal loss of accuracy, even under scenarios where the edge server is overloaded or the network latency is significant. Finally, Drolia et al [155,162] examine the trade-off between the accuracy and latency of computer vision algorithms. The authors find that the accuracy increases along with an increase in latency as the number of extracted features from an image increases.…”

Section: Augmented Reality and Continuous Mobile Visionmentioning

confidence: 99%

Video Caching, Analytics, and Delivery at the Wireless Edge: A Survey and Future Directions

Jedari

Premsankar

Illahi

et al. 2021

IEEE Commun. Surv. Tutorials

View full text Add to dashboard Cite

Cachier: Edge-Caching for Recognition Applications

Cited by 131 publications

References 25 publications

All one needs to know about fog computing and related edge computing paradigms: A complete survey

All one needs to know about fog computing and related edge computing paradigms: A complete survey

Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing

Video Caching, Analytics, and Delivery at the Wireless Edge: A Survey and Future Directions

Contact Info

Product

Resources

About