DeepWear: Adaptive local offloading for on-wearable deep learning

Mengwei Xu, Feng Qian, Mengze Zhu, Feifan Huang, Saumay Pushp, Xuanzhe Liu

Research output: Contribution to journalArticlepeer-review

82 Scopus citations


Due to their on-body and ubiquitous nature, wearables can generate a wide range of unique sensor data creating countless opportunities for deep learning tasks. We propose DeepWear, a deep learning (DL) framework for wearable devices to improve the performance and reduce the energy footprint. DeepWear strategically offloads DL tasks from a wearable device to its paired handheld device through local network connectivity such as Bluetooth. Compared to the remote-cloud-based offloading, DeepWear requires no Internet connectivity, consumes less energy, and is robust to privacy breach. DeepWear provides various novel techniques such as context-aware offloading, strategic model partition, and pipelining support to efficiently utilize the processing capacity from nearby paired handhelds. Deployed as a user-space library, DeepWear offers developer-friendly APIs that are as simple as those in traditional DL libraries such as TensorFlow. We have implemented DeepWear on the Android OS and evaluated it on COTS smartphones and smartwatches with real DL models. DeepWear brings up to 5.08X and 23.0X execution speedup, as well as 53.5 and 85.5 percent energy saving compared to wearable-only and handheld-only strategies, respectively.

Original languageEnglish (US)
Article number8618364
Pages (from-to)314-330
Number of pages17
JournalIEEE Transactions on Mobile Computing
Issue number2
StatePublished - Feb 1 2020

Bibliographical note

Publisher Copyright:
© 2002-2012 IEEE.


  • Wearables
  • deep learning
  • offloading


Dive into the research topics of 'DeepWear: Adaptive local offloading for on-wearable deep learning'. Together they form a unique fingerprint.

Cite this