Filters








11 Hits in 1.4 sec

DeepCache

Mengwei Xu, Mengze Zhu, Yunxin Liu, Felix Xiaozhu Lin, Xuanzhe Liu
2018 Proceedings of the 24th Annual International Conference on Mobile Computing and Networking - MobiCom '18  
We present DeepCache, a principled cache design for deep learning inference in continuous mobile vision.  ...  It addresses a key challenge raised by mobile vision: the cache must operate under video scene variation, while trading off among cacheability, overhead, and loss in model accuracy.  ...  . • We present DeepCache, a principled cache for executing CNN over mobile videos (Section 3).  ... 
doi:10.1145/3241539.3241563 dblp:conf/mobicom/XuZLLL18 fatcat:w4pwzh3trjeb5ealpwq4i6c4ea

Boosting Mobile CNN Inference through Semantic Memory [article]

Yun Li, Chen Zhang, Shihao Han, Li Lyna Zhang, Baoqun Yin, Yunxin Liu, Mengwei Xu
2021 arXiv   pre-print
SMTM is prototyped on commodity CNN engine and runs on both mobile CPU and GPU.  ...  low-cost yet accurate cache and lookup; (2) it uses a novel metric in determining the exit timing considering different layers' inherent characteristics; (3) it adaptively adjusts the cache size and semantic  ...  In Proceedings of the 18th International DeepCache: Principled cache for mobile deep vision.  ... 
arXiv:2112.02644v1 fatcat:gfyecsojvzgaxjgmlwihov26ju

CacheNet: A Model Caching Framework for Deep Learning Inference on the Edge [article]

Yihao Fang, Shervin Manzuri Shalmani, Rong Zheng
2020 arXiv   pre-print
The success of deep neural networks (DNN) in machine perception applications such as image classification and speech recognition comes at the cost of high computation and storage complexity.  ...  In order to have the best of both worlds (latency and accuracy), we propose CacheNet, a model caching framework.  ...  In [21] , Xu et al. proposed DeepCache, a principled cache design for deep learning inference in continuous mobile vision.  ... 
arXiv:2007.01793v1 fatcat:ygoeavc6d5cubbtgewylyaeb5y

Convergence of Edge Computing and Deep Learning: A Comprehensive Survey [article]

Xiaofei Wang and Yiwen Han and Victor C.M. Leung and Dusit Niyato and Xueqiang Yan and Xu Chen
2019 arXiv   pre-print
However, due to efficiency and latency issues, the current cloud computing service architecture hinders the vision of "providing artificial intelligence for every person and every organization at everywhere  ...  As an important enabler broadly changing people's lives, from face recognition to ambitious smart factories and cities, developments of artificial intelligence (especially deep learning, DL) based applications  ...  DeepCache [165] performs cache key lookup to solve this.  ... 
arXiv:1907.08349v2 fatcat:4hfqgdto4fhvlguwfjxuz3ik5q

Deep Learning in Mobile and Wireless Networking: A Survey [article]

Chaoyun Zhang, Paul Patras, Hamed Haddadi
2019 arXiv   pre-print
Drawing from our experience, we discuss how to tailor deep learning to mobile environments. We complete this survey by pinpointing current challenges and open future directions for research.  ...  We then discuss several techniques and platforms that facilitate the efficient deployment of deep learning onto mobile systems.  ...  In [530] , Xu et al. accelerate deep learning inference for mobile vision from the caching perspective.  ... 
arXiv:1803.04311v3 fatcat:awuvyviarvbr5kd5ilqndpfsde

Deep Learning in Mobile and Wireless Networking: A Survey

Chaoyun Zhang, Paul Patras, Hamed Haddadi
2019 IEEE Communications Surveys and Tutorials  
Drawing from our experience, we discuss how to tailor deep learning to mobile environments. We complete this survey by pinpointing current challenges and open future directions for research.  ...  We then discuss several techniques and platforms that facilitate the efficient deployment of deep learning onto mobile systems.  ...  In [533] , Xu et al. accelerate deep learning inference for mobile vision from the caching perspective.  ... 
doi:10.1109/comst.2019.2904897 fatcat:xmmrndjbsfdetpa5ef5e3v4xda

C^3DRec: Cloud-Client Cooperative Deep Learning for Temporal Recommendation in the Post-GDPR Era [article]

Jialiang Han, Yun Ma
2021 arXiv   pre-print
To realize the temporal recommendation in the post-GDPR era, this paper proposes C^3DRec, a cloud-client cooperative deep learning framework of mining interaction behaviors for recommendation while preserving  ...  Mobile devices enable users to retrieve information at any time and any place.  ...  DeepCache: Principled cache for mobile deep vision.  ... 
arXiv:2101.05641v1 fatcat:c2j5dhunubblrb3cocgvrcr4ay

Deep Neural Mobile Networking [article]

Chaoyun Zhang
2020 arXiv   pre-print
This thesis attacks important problems in the mobile networking area from various perspectives by harnessing recent advances in deep neural networks.  ...  in mobile networks.  ...  In [156] , Xu et al. accelerate deep learning inference for mobile vision from the caching perspective.  ... 
arXiv:2011.05267v1 fatcat:yz2zp5hplzfy7h5kptmho7mbhe

GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsity [article]

Wei Niu, Zhengang Li, Xiaolong Ma, Peiyan Dong, Gang Zhou, Xuehai Qian, Xue Lin, Yanzhi Wang, Bin Ren
2021 arXiv   pre-print
It is appealing but challenging to achieve real-time deep neural network (DNN) inference on mobile devices because even the powerful modern mobile devices are considered as "resource-constrained" when  ...  and high accuracy, leveraging fine-grained structured sparse model Inference and compiler optimizations for Mobiles.  ...  RELATED WORK There have been many efforts on DNN acceleration frameworks on mobiles, like DeepEar [57] , MCDNN [58] , Deep-Mon [59] , DeepSense [60] , DeepCache [61] , etc.  ... 
arXiv:2108.11033v1 fatcat:mjoxwkfesjhxhhpl7bj6leqwoy

Distributed placement and resource orchestration of real-time edge computing applications

Wuyang Zhang
2021
The recent emergence of a broad class of deep learning based augmented and virtual reality applications motivates the need for real-time mobile cloud services.  ...  These real-time, mobile applications involve intensive computation over large data sets, and are generally required to provide low end-to-end latency for acceptable quality-of-experience at the end-user  ...  DeepCache [186] caches and reuses the result of convolutional operations to reduce the repeated computation.  ... 
doi:10.7282/t3-ryxr-6g54 fatcat:byb752v6tnavff6vals2mfk2cu

Empowering video applications for mobile devices [article]

He, Jian (Ph. D. In Computer Science), Austin, The University Of Texas At, Lili Qiu
2020
We identify a few major challenges to guarantee high user experience for running video applications on mobile devices. First, existing video applications call for high-resolution videos(e.g., 4K).  ...  It is critical to design a light-weight video codec to provide fast video coding as well as high compression e ciency for mobile devices.  ...  Deep compression and cache can be applied to our work to speed up inference.  ... 
doi:10.26153/tsw/10178 fatcat:vsa5x5jupbgfro4jepmopglify