DeepCache: Principled Cache for Mobile Deep Vision

@article{Xu2018DeepCachePC,
  title={DeepCache: Principled Cache for Mobile Deep Vision},
  author={Mengwei Xu and Mengze Zhu and Yunxin Liu and F. Lin and Xuanzhe Liu},
  journal={Proceedings of the 24th Annual International Conference on Mobile Computing and Networking},
  year={2018}
}
  • Mengwei Xu, Mengze Zhu, +2 authors Xuanzhe Liu
  • Published 2018
  • Computer Science
  • Proceedings of the 24th Annual International Conference on Mobile Computing and Networking
We present DeepCache, a principled cache design for deep learning inference in continuous mobile vision. DeepCache benefits model execution efficiency by exploiting temporal locality in input video streams. 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. At the input of a model, DeepCache discovers video temporal locality by exploiting the video's internal… Expand
Elf: accelerate high-resolution mobile deep vision with content-aware parallel offloading
CacheNet: A Model Caching Framework for Deep Learning Inference on the Edge
FlexDNN: Input-Adaptive On-Device Deep Learning for Efficient Mobile Vision
CBinfer: Exploiting Frame-to-Frame Locality for Faster Convolutional Network Inference on Video Streams
  • L. Cavigelli, L. Benini
  • Computer Science
  • IEEE Transactions on Circuits and Systems for Video Technology
  • 2020
NEMO: enabling neural-enhanced video streaming on commodity mobile devices
GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsity.
  • Wei Niu, Zhengang, +6 authors Bin Ren
  • Medicine
  • IEEE transactions on pattern analysis and machine intelligence
  • 2021
Mistify: Automating DNN Model Porting for On-Device Inference at the Edge
MemA: Fast Inference of Multiple Deep Models
...
1
2
3
4
5
...

References

SHOWING 1-8 OF 8 REFERENCES
DeepMon: Mobile GPU-based Deep Learning Framework for Continuous Vision Applications
CBinfer: Change-Based Inference for Convolutional Neural Networks on Video Data
ImageNet classification with deep convolutional neural networks
UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
A new diamond search algorithm for fast block matching motion estimation
  • Shan Zhu, K. Ma
  • Mathematics
  • Proceedings of ICICS, 1997 International Conference on Information, Communications and Signal Processing. Theme: Trends in Information Systems Engineering and Wireless Multimedia Communications (Cat.
  • 1997
ImageNet Classication with Deep Convolutional Neural Networks
  • In Proceedings of the 26th Annual Conference on Neural Information Processing Systems
  • 2012