Jeff Donahue

I'm a fourth-year Ph.D. student in computer science at UC Berkeley, researching computer vision and machine learning advised by Trevor Darrell.

I graduated from UT Austin in May 2011 with a B.S. in Computer Science, completing a Turing Scholars degree with an honors thesis (December 2010) supervised by Kristen Grauman.


J. Donahue, L. Hendricks, S. Guadarrama, M. Rohrbach, S. Venugopalan, K. Saenko, T. Darrell.
Long-term Recurrent Convolutional Networks for Visual Recognition and Description [pdf].
arXiv:1411.4389, November 2014.

J. Hoffman, S. Guadarrama, E. Tzeng, R. Hu, J. Donahue, R. Girshick, T. Darrell, K. Saenko.
LSDA: Large Scale Detection Through Adaptation [pdf].
To appear in Proceedings of the Neural Information Processing Systems Conference (NIPS), Montreal, Canada, December 2014.

S. Guadarrama, E. Rodner, K. Saenko, N. Zhang, R. Farrell, J. Donahue, T. Darrell.
Open-vocabulary Object Retrieval.
In Proceedings of the Robotics: Science and Systems Conference (RSS, oral), Berkeley, California, July 2014.

Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, T. Darrell.
Caffe: Convolutional Architecture for Fast Feature Embedding [pdf (arXiv)].
arXiv:1408.5093, June 2014.
Winner of the 2014 ACM MM Open Source Software Competition! (Orlando, Florida, November 2014)
Download Caffe

N. Zhang, J. Donahue, R. Girshick, T. Darrell.
Part-based R-CNNs for Fine-grained Category Detection [pdf (arXiv)].
In Proceedings of the European Conference on Computer Vision (ECCV, oral), Zurich, Switzerland, September 2014.

R. Girshick, J. Donahue, T. Darrell, J. Malik.
Rich feature hierarchies for accurate object detection and semantic segmentation [extended pdf (arXiv)].
In Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR, oral), Columbus, Ohio, June 2014.

J. Donahue*, Y. Jia*, O. Vinyals, J. Hoffman, N. Zhang, E. Tzeng, T. Darrell.
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition [pdf].
In Proceedings of the International Conference on Machine Learning (ICML), Beijing, China, June 2014.

E. Rodner, J. Hoffman, J. Donahue, T. Darrell, and K. Saenko.
Towards Adapting ImageNet to Reality: Scalable Domain Adaptation with Implicit Low-rank Transformations [pdf].
arXiv:1308.4200, August 2013.

J. Donahue, J. Hoffman, E. Rodner, K. Saenko, and T. Darrell.
Semi-Supervised Domain Adaptation with Instance Constraints.
In Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Portland, Oregon, June 2013.

J. Hoffman, E. Rodner, J. Donahue, K. Saenko, and T. Darrell.
Efficient Learning of Domain-Invariant Image Representations.
In Proceedings of the International Conference on Learning Representations (ICLR), Scottsdale, Arizona, May 2013.

J. Donahue and K. Grauman.
Annotator Rationales for Visual Recognition.
In Proceedings of the International Conference on Computer Vision (ICCV), Barcelona, Spain, November 2011.

J. Donahue.
Image Classification with Annotator Rationales.
The University of Texas at Austin, Department of Computer Sciences. Report #HR-10-10 (honors theses). December 2010.

Industry Experience

Fall 2014 to present: part-time engineer with Pinterest - Visual Discovery

Summer 2014: interned with Pinterest - Visual Discovery

Summer 2010-2012: interned with Google - Image Search Annotation (Summer 2012), Mobile Search Ad Quality (Summer 2011), YouTube Content Management System (Summer 2010)

Summer 2008-2009: interned with National Instruments - LabVIEW EIO Variable Architecture (Summer 2009), LabVIEW FPGA (Summer 2008)

Other Stuff

Wrote Smozzy, an Android app that lets users without a data plan browse the web through text messaging (covered in several tech journals, including TechCrunch, CNET, Engadget, etc.).

Last updated 11/19/2014.