150 citations · 210 across the 6 of their papers we have counts for
6 papers
Automated Backend-Aware Post-Training Quantization
Ziheng Jiang, Animesh Jain, Andrew Liu +4
Quantization is a key technique to reduce the resource requirement and improve the performance of neural network deployment. However, different hardware backends such as x86 CPU, N…
SplitSR: An End-to-End Approach to Super-Resolution on Mobile Devices
Xin Liu, Yuang Li, Josh Fromm +4
Super-resolution (SR) is a coveted image processing technique for mobile apps ranging from the basic camera apps to mobile health. Existing SR algorithms rely on deep learning mode…
MetaPhys: Few-Shot Adaptation for Non-Contact Physiological Measurement
Xin Liu, Ziheng Jiang, Josh Fromm +3
There are large individual differences in physiological processes, making designing personalized health sensing algorithms challenging. Existing machine learning systems struggle t…
Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement
Xin Liu, Josh Fromm, Shwetak Patel +1
Telehealth and remote health monitoring have become increasingly important during the SARS-CoV-2 pandemic and it is widely expected that this will have a lasting impact on healthca…
Heterogeneous Bitwidth Binarization in Convolutional Neural Networks
Josh Fromm, Shwetak Patel, Matthai Philipose
Recent work has shown that fast, compact low-bitwidth neural networks can be surprisingly accurate. These networks use homogeneous binarization: all parameters in each layer or (mo…
Precision Scaling of Neural Networks for Efficient Audio Processing
Jong Hwan Ko, Josh Fromm, Matthai Philipose +2
While deep neural networks have shown powerful performance in many audio applications, their large computation and memory demand has been a challenge for real-time processing. In t…