Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers

12/19/2020
by   Romil Bhardwaj, et al.
12

Video analytics applications use edge compute servers for the analytics of the videos (for bandwidth and privacy). Compressed models that are deployed on the edge servers for inference suffer from data drift, where the live video data diverges from the training data. Continuous learning handles data drift by periodically retraining the models on new data. Our work addresses the challenge of jointly supporting inference and retraining tasks on edge servers, which requires navigating the fundamental tradeoff between the retrained model's accuracy and the inference accuracy. Our solution Ekya balances this tradeoff across multiple models and uses a micro-profiler to identify the models that will benefit the most by retraining. Ekya's accuracy gain compared to a baseline scheduler is 29 resources to achieve the same accuracy as Ekya.

READ FULL TEXT

page 3

page 5

page 11

research
03/25/2023

Edge-Based Video Analytics: A Survey

Edge computing has been getting a momentum with ever-increasing data at ...
research
06/27/2023

DeepStream: Bandwidth Efficient Multi-Camera Video Streaming for Deep Learning Analytics

Deep learning video analytic systems process live video feeds from multi...
research
05/18/2021

Towards Performance Clarity of Edge Video Analytics

Edge video analytics is becoming the solution to many safety and managem...
research
11/10/2021

Towards Live Video Analytics with On-Drone Deeper-yet-Compatible Compression

In this work, we present DCC(Deeper-yet-Compatible Compression), one ena...
research
05/25/2023

Privacy Protectability: An Information-theoretical Approach

Recently, inference privacy has attracted increasing attention. The infe...
research
09/09/2020

ODIN: Automated Drift Detection and Recovery in Video Analytics

Recent advances in computer vision have led to a resurgence of interest ...
research
01/19/2022

GEMEL: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge

Video analytics pipelines have steadily shifted to edge deployments to r...

Please sign up or login with your details

Forgot password? Click here to reset