SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1712.01670 · 2017

DeepCache: Principled Cache for Mobile Deep Vision

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 structure, for which it borrows proven heuristics from video compression; into the model, DeepCache propagates regions of reusable results by exploiting the model's internal structure. Notably, DeepCache eschews applying video heuristics to model internals which are not pixels but high-dimensional, difficult-to-interpret data. Our implementation of DeepCache works with unmodified deep learning models, requires zero developer's manual effort, and is therefore immediately deployable on off-the-shelf mobile devices. Our experiments show that DeepCache saves inference execution time by 18% on average and up to 47%. DeepCache reduces system energy consumption by 20% on average.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1712.01670")
get_code_for_paper("1712.01670")
have("1712.01670")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1712.01670.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1712.01670.svg)](https://syntology.ai/paper/1712.01670)

Connect an agent — have() is free.