Object detection is arguably one of central problems in computer vision. Much progress has been made over the past few years in deep learning based object detectors. Despite their impressive accuracy results on standard benchmarks, these models come at a price of their complexity and computational cost. This imposes a major barrier to deploy these […]
Category: Paper digest
SONIC: The Serverless Data Corraller
This is a high-level view of our work on serverless computing that has just been accepted to Usenix ATC 2021, plus some historical context for why we are where we are. And a look ahead at the rich problems that we still have to tame. Ashraf Mahgoub (Purdue University), Karthick Shankar (Carnegie Mellon University), Subrata […]