[Colloquium] Kuntai Du MS Presentation/Mar 8, 2022

[Megan Woodward]

This is an announcement of Kuntai Du's MS Presentation
===============================================
Candidate: Kuntai Du

Date: Tuesday, March 08, 2022

Time:  4 pm CST

Remote Location:  https://uchicago.zoom.us/j/4015085138?pwd=eU5ZNzc3Mmg3bTFiQ2E3ejZqSXlWQT09

M.S. Paper Title: AccMPEG: Optimizing Video Encoding for Accurate Video Analytics

Abstract: With more videos being recorded by edge sensors (cameras) and analyzed by computer-vision deep neural nets (DNNs), a new breed of video streaming systems has emerged, with the goal to compress and stream videos to remote servers in real time while preserving enough information to allow highly accurate inference by the server-side DNNs.  An ideal design of the video streaming system should simultaneously meet three key requirements: (1) low latency of encoding and streaming, (2) high accuracy of server-side DNNs, and (3) low compute overheads on the camera.Unfortunately, despite many recent efforts, such video streaming system has hitherto been elusive, especially when serving advanced vision tasks such as object detection or semantic segmentation. This paper presents AccMPEG, a new video encoding and streaming system that meets the three objectives. The key is to learn how much the encoding quality at each (16x16) macroblock can influence the server-side DNN accuracy, which we call accuracy gradients. Our insight is that these macroblock-level accuracy gradients can be inferred with sufficient precision by feeding the video frames through a cheap model. AccMPEG provides a suite of techniques that, given a new server-side DNN, can quickly create a cheap model to infer the accuracy gradients on any new frame in near realtime. Our extensive evaluation of AccMPEG on two types of edge devices (one Intel Xeon Silver 4100 CPU or NVIDIA Jetson Nano) and three vision tasks (six recent pre-trained DNNs) shows that compared to the state-of-the-art baselines, AccMPEG (with the same camera-side compute resources) can reduce the end-to-end inference delay by 10-43% without hurting accuracy.
% or increase accuracy by 0.5-2% without incurring more delays.

Advisors: Junchen Jiang

Committee Members: Shan Lu, Junchen Jiang, Sanjay Krishnan, and Nick Feamster







-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20220304/5a9f1494/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: AccMPEG_MasterDefense (1).pdf
Type: application/pdf
Size: 7645226 bytes
Desc: AccMPEG_MasterDefense (1).pdf
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20220304/5a9f1494/attachment-0001.pdf>