Judy Hoffman - Graduate Student in Computer Vision at UC Berkeley

Judy Hoffman
jhoffman at eecs.berkeley.edu

Research

Industry
Experience

Teaching
Experience

Service

Distinctions

About me

I am a third year PhD student interested in the development and application of Machine Learning algorithms to Computer Vision problems. My current projects focus on the specific task of Domain Adaptation for Object Recognition. I collaborate with my advisors, Trevor Darrell and Kate Saenko, as well as the the Berkeley Computer Vision group.

My undergraduate research focused on developing motion planning algorithms for Robotics in the Automation Sciences Lab at UC Berkeley with Professor Ken Goldberg. I graduated from UC Berkeley with a BS in Electrical Engineering and Computer Science in Spring 2010.

My CV is available here.

Research Projects

For more details about my research and for data/code downloads, visit my research project page.

	New! Efficient Learning of Domain-invariant Image Representations Judy Hoffman, Erik Rodner, Jeff Donahue, Kate Saenko, Trevor Darrell International Conference on Learning Representations (ICLR), 2013. (Oral) bibtex / talk / code We learn a category invariant feature transformation, which maps target points into the source domain such that they corrected classified by the source classifier.
	New! Semi-Supervised Domain Adaptation with Instance Constraints Jeff Donahue, Judy Hoffman, Erik Rodner, Kate Saenko, Trevor Darrell Computer Vision and Pattern Recognition (CVPR), 2013. bibtex By using instance constraints, available through tracking or other methods, we can improve unsupervised domain adaptation performance.
	Discovering Latent Domains For Multisource Domain Adaptation Judy Hoffman, Brian Kulis, Trevor Darrell, Kate Saenko European Conference in Computer Vision (ECCV), 2012. supplementary material / bibtex / poster / video / code We learn to separate large heterogeneous data sources into multiple latent visual domains and show that using this learned clustering improves classification performance.
	Weakly Supervised Learning of Object Segmentations from Web-Scale Video Glen Hartmann, Matthias Grundmann, Judy Hoffman, David Tsai, Vivek Kwatra, Omid Madani, Sudheendra Vijayanarasimhan, Irfan Essa, James Rehg, Rahul Sukthankar European Conference in Computer Vision (ECCV) Workshop on Web-scale Vision and Social Media, 2012. (Best Paper Award) bibtex We learn segment level video classification using videos with only weakly labeled tag information.
	Domain Adaptation with Multiple Latent Domains Judy Hoffman, Kate Saenko, Brian Kulis, Trevor Darrell NIPS Domain Adaptation Workshop Talk, 2011. (Best Student Paper Award) We present a method for multi-source adaptation with latent source domains. See ECCV2012 paper for more details.
	EG-RRT: Environment-Guided Random Trees for Kinodynamic Motion Planning with Uncertainty and Obstacles Leonard Jaillet, Judy Hoffman, Jur van den Berg, Pieter Abbeel, Josep M. Porta, Ken Goldberg IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2011. bibtex