Favyen Bastani

Contact: favyen@perennate.com

About: I am a PhD student in computer science at the Massachusetts Institute of Technology working with Sam Madden in the database research group.

Research: I am interested in systems and machine learning methods for analyzing imagery and video data at scale, especially in interactive data analysis settings. I've worked on both methods to reduce the computational cost of processing video, and methods to reduce the hand-labeling time needed to create training datasets suitably large to train high-accuracy models.

I have also worked on developing machine learning approaches that are tailored for processing geo-spatial data such as aerial and satellite imagery. Geo-spatial data often involves unique data types such as road networks, and models that better represent these data types can offer improved accuracy.

Publications

SkyQuery: Optimizing Video Queries over UAVs. Favyen Bastani, Osbert Bastani, Songtao He, Arjun Balasingam, Ziwen Jiang, Radhika Mittal, Mohammad Alizadeh, Hari Balakrishnan, Tim Kraska, and Sam Madden. In submission. [pdf]

A Self-Supervised Approach for Recognizing Street Map Changes using Satellite Imagery. Favyen Bastani, Songtao He, Satvat Jagwani, Edward Park, Sofiane Abbar, Mohammad Alizadeh, Hari Balakrishnan, Sanjay Chawla, Mohamed Elshrif, Sam Madden, and Mohammad Amin Sadeghi. In submission. [pdf]

MIRIS: Fast Object Track Queries in Video. Favyen Bastani, Songtao He, Arjun Balasingam, Karthik Gopalakrishnan, Mohammad Alizadeh, Hari Balakrishnan, Michael Cafarella, Tim Kraska, and Sam Madden. SIGMOD 2020. [pdf] [web]

RoadTagger: Robust Road Attribute Inference with Graph Neural Networks. Songtao He, Favyen Bastani, Satvat Jagwani, Edward Park, Sofiane Abbar, Mohammad Alizadeh, Hari Balakrishnan, Sanjay Chawla, Sam Madden, and Mohammad Amin Sadeghi. AAAI 2020. [arxiv]

Machine-Assisted Map Editing. Favyen Bastani, Songtao He, Sofiane Abbar, Mohammad Alizadeh, Hari Balakrishnan, Sanjay Chawla, and Sam Madden. SIGSPATIAL 2018. [pdf] [web] [code]

RoadRunner: Improving the Precision of Road Network Inference from GPS Trajectories. Songtao He, Favyen Bastani, Sofiane Abbar, Mohammad Alizadeh, Hari Balakrishnan, Sanjay Chawla, and Sam Madden. SIGSPATIAL 2018. [pdf] [web]

RoadTracer: Automatic Extraction of Road Networks from Aerial Images. Favyen Bastani, Songtao He, Sofiane Abbar, Mohammad Alizadeh, Hari Balakrishnan, Sanjay Chawla, Sam Madden, and David DeWitt. CVPR 2018. [pdf] [web] [code]

Large Scale Real-time Ridesharing with Service Guarantee on Road Networks. Yan Huang, Favyen Bastani, Ruoming Jin, and Xiaoyang Sean Wang. VLDB 2014. [pdf] [code]

A Greener Transportation Mode: Flexible Routes Discovery from GPS Trajectory Data. Favyen Bastani, Yan Huang, Xing Xie, and Jason Powell. SIGSPATIAL 2011. [pdf]

Code

RoadTracer aims to improve the accuracy of inferring road networks from satellite imagery through an iterative graph construction procedure. The code is available in Github, with an improved version available here.

gobearmon is a simple but reliable distributed uptime monitoring system that can send alerts over e-mail and SMS when services go offline.