Christopher Kanan Headshot

Christopher Kanan

Assistant Professor
Chester F. Carlson Center for Imaging Science
College of Science

Office Location

Christopher Kanan

Assistant Professor
Chester F. Carlson Center for Imaging Science
College of Science


BS, Oklahoma State University; MS, University of Southern California; Ph.D., University of California


I’m an Assistant Professor in the Carlson Center for Imaging Science at the Rochester Institute of Technology (RIT). I’m also Associate Director of RIT’s Center for Human-aware AI (CHAI), and Affiliate Faculty in RIT’s Computer Science Department. I am a member of the McNair Scholars Advisory Board, part of RIT’s Division of Diversity and Inclusion. I direct the Machine and Neuromorphic Perception Laboratory (a.k.a., kLab). I’m also a Senior AI Scientist at PAIGE, where we are developing deep learning algorithms to better detect and treat cancer. 


My lab’s main focus is basic research in task-driven scene understanding and lifelong machine learning. Our recent work has focused on visual question answering (VQA) and incremental learning in deep networks. We also do applied research in using deep learning to solve problems in computer vision. In the past, I have worked on semantic segmentation, object recognition, object detection, active vision, object tracking, and more. Beyond machine learning, I also have a strong background in eye tracking, primate vision, and theoretical neuroscience.


Areas of Expertise

Currently Teaching

1 - 4 Credits
This course is a faculty-directed tutorial of appropriate topics that are not part of the formal curriculum. The level of study is appropriate for student in their graduate studies.
0 Credits
Continuation of Thesis
1 - 6 Credits
Doctoral-level research by the candidate on an appropriate topic as arranged between the candidate and the research advisor.
0 Credits
This course is a cooperative education experience for graduate imaging science students.
3 Credits
This course will review neural networks and related theory in machine learning that is needed to understand how deep learning algorithms work. The course will include the latest algorithms that use deep learning to solve problems in computer vision and machine perception, and students will read recent papers on these systems. Students will implement and evaluate one or more of these systems and apply them to problems that match their interests. Students are expected to have taken multiple computer programming courses and to be comfortable with linear algebra and calculus. No prior background in machine learning or pattern recognition is required.
3 Credits
This course will cover a wide range of current topics in modern still digital image processing. Topics will include grey scale and color image formation, color space representation of images, image geometry, image registration and resampling, image contrast manipulations, image fusion and data combining, point spatial and neighborhood operations, image watermarking and steganography, image compression, spectral data compression, image segmentation and classification, and basic morphological operators. Projects will involve advanced computational implementations of selected topics from the current literature in a high level language such as Matlab or IDL and will be summarized by the students in written technical papers.

In the News

Select Scholarship

Journal Paper
Birmingham, E, et al. "Exploring Emotional Expression Recognition in Aging Adults using the Moving Window Technique." PLOS ONE. (2018): N/A. Web.
Kemker, Ron, Ryan Luu, and Christopher Kanan. "Low-Shot Learning for the Semantic Segmentation of Remote Sensing Imagery." IEEE Transactions on Geoscience and Remote Sensing (TGRS). (2018): 6214 - 6223. Print.
Kemker, R, C Salvaggio, and C Kanan. "Algorithms for Semantic Segmentation of Multispectral Remote Sensing Imagery using Deep Learning." ISPRS Journal of Photogrammetry and Remote Sensing. (2018): 60-77. Print.
Published Conference Proceedings
Kafle, Kushal, et al. "DVQA: Understanding Data Visualizations via Question Answering." Proceedings of the Computer Vision and Pattern Recognition (CVPR). Ed. N/A. Salt Lake City, Utah: n.p., 2018. Web.
Hayes, Tyler, Ronald Kemker, and Christopher Kanan. "New Metrics and Experimental Paradigms for Continual Learning." Proceedings of the Real-World Challenges and New Benchmarks for Deep Learning in Robotic Vision (CVPRW). Ed. N/A. Salt Lake City, Utah: n.p., 2018. Web.
Binaee, K, et al. "Characterizing the Temporal Dynamics of Information in Visually Guided Predictive Control Using LSTM Recurrent Neural Networks." Proceedings of the 40th Annual Conference of the Cognitive Science Society (CogSci-2018). Ed. N/A. Madison, WI: n.p., 2018. Web.
Kemker, Ronald and Christopher Kanan. "FearNet: Brain-Inspired Model for Incremental Learning." Proceedings of the International Conference on Learning Representations (ICLR-2018). Ed. N/A. Vancouver, Canada: n.p., 2018. Web.
Kemker, R, et al. "Measuring Catastrophic Forgetting in Neural Networks." Proceedings of the AAAI-2018. Ed. N/A. New Orleans, LA: n.p., 2018. Web.
Kafle, Kushal and Christopher Kanan. "Answer-Type Prediction for Visual Question Answering." Proceedings of the IEEE Computer Vision and Pattern Recognition Conference 2016 (CVPR-2016). Ed. IEEE. Las Vegas, NV: IEEE, 2016. Web.
Yousefhussien, Mohammed, N. Andrew Browning, and Christopher Kanan. "Online Tracking using Saliency." Proceedings of the IEEE Winter Applications of Computer Vision Conference (WACV-2016). Ed. N/A. Lake Placid, New York: IEEE, 2016. Print.