arXiv subjects

Peter Bodik

Publications and source records attributed to Peter Bodik.

3 recordsLinked to original sources

arXiv2023

Evaluating how interactive visualizations can assist in finding samples where and how computer vision models make mistakes

Creating Computer Vision (CV) models remains a complex practice, despite their ubiquity. Access to data, the requirement for ML expertise, and model opacity are just a few points of complexity that limit the ability of end-users to build, inspect, and improve these models. Interactive ML perspectives have helped address some of these issues by considering a teacher in the loop where planning, teaching, and evaluating tasks take place. We present and evaluate two interactive visualizations in the context of Sprite, a system for creating CV classification and detection models for images originating from videos. We study how these visualizations help Sprite's users identify (evaluate) and select (plan) images where a model is struggling and can lead to improved performance, compared to a baseline condition where users used a query language. We found that users who had used the visualizations found more images across a wider set of potential types of model errors.

cs.HC↗

arXiv2018

Unified Management and Optimization of Edge-Cloud IoT Applications

Internet of Things (IoT) applications have seen a phenomenal growth with estimates of growing to a 25 Billion dollar industry by 2020. With the scale of IoT applications growing and stricter requirements on latency, edge computing has piqued the interest for such environments. However, the industry is still in its infancy with no proper support for applications running across the entire edge-cloud environment, and an array of manual tedious per-application optimizations. In this work, we propose Steel, a unified framework for developing, deploying, and monitoring applications in the edge-cloud. Steel supports dynamically adapting and easily moving services back and forth between the edge and the cloud. Steel is extensible where common optimizations (but crucial for the edge) can be built as pluggable and configurable modules. We have added two very common optimizations: placement and adaptive communication, to cope with both short and long-term changes in the workload and environment.

cs.DC↗

arXiv2018

Focus: Querying Large Video Datasets with Low Latency and Low Cost

Large volumes of videos are continuously recorded from cameras deployed for traffic control and surveillance with the goal of answering "after the fact" queries: identify video frames with objects of certain classes (cars, bags) from many days of recorded video. While advancements in convolutional neural networks (CNNs) have enabled answering such queries with high accuracy, they are too expensive and slow. We build Focus, a system for low-latency and low-cost querying on large video datasets. Focus uses cheap ingestion techniques to index the videos by the objects occurring in them. At ingest-time, it uses compression and video-specific specialization of CNNs. Focus handles the lower accuracy of the cheap CNNs by judiciously leveraging expensive CNNs at query-time. To reduce query time latency, we cluster similar objects and hence avoid redundant processing. Using experiments on video streams from traffic, surveillance and news channels, we see that Focus uses 58X fewer GPU cycles than running expensive ingest processors and is 37X faster than processing all the video at query time.

cs.DB↗