Konstantinos (Kosta) Derpanis

Associate Professor. CS. Computer Vision. Machine Learning

I am an Associate Professor in the Department of Electical Engineering and Computer Science at York University, Toronto, Canada. I am also a Vector Institute Faculty Affiliate, an ELLIS Member and a Visting Professor at the Samsung AI Centre Toronto. I am currently serving as an Associate Editor for the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) and will serve as a Program Chair for IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR) 2028.

Research Interests: My main interests are computer vision, deep learning, generative AI, and interpretability.

news

July 1, 2025 On sabbatical between July 1, 2025 and June 30, 2026. Visiting Carnegie Mellon (Fall 2025), Ludwig Maximilian University of Munich (Winter 2026), and the University of Zurich (Spring-Summer 2026).

selected publications

ICML
Universal sparse autoencoders: Interpretable cross-model concept alignment
Harrish Thasarathan, Julian Forsyth, Thomas Fel, Matthew Kowal, and Konstantinos G. Derpanis
In International Conference on Machine Learning, 2025
Abs PDF
CVPR
Visual concept connectome (VCC): Open world concept discovery and their interlayer connections in deep models
Matthew Kowal, Richard P. Wildes, and Konstantinos G. Derpanis
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
Abs PDF
CVPR
Understanding video transformers via universal concept discovery
Matthew Kowal, Achal Dave, Rares Ambrus, Adrien Gaidon, Konstantinos G. Derpanis, and Pavel Tokmakov
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
Abs PDF
TPAMI
Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks
Matthew Kowal, Mennatullah Siam, Md. Amirul Islam, Neil D. B. Bruce, Richard P. Wildes, and Konstantinos G. Derpanis
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025
Abs PDF
IJCV
Position, padding and predictions: A deeper look at position information in CNNs
Md. Amirul Islam, Matthew Kowal, Sen Jia, Konstantinos G. Derpanis, and Neil D. B. Bruce
International Journal of Computer Vision, 2024
ECCV
PolyOculus: Simultaneous Multi-view Image-based Novel View Synthesis
Jason J. Yu, Tristan Aumentado-Armstrong, Fereshteh Forghani, Konstantinos G. Derpanis, and Marcus A. Brubaker
In European Conference on Computer Vision, 2024
Abs PDF
ECCV
Watch your steps: Local image and scene editing by text instructions
Ashkan Mirzaei, Tristan Aumentado-Armstrong, Marcus A. Brubaker, Jonathan Kelly, Alex Levinshtein, Konstantinos G. Derpanis, and Igor Gilitschenski
In European Conference on Computer Vision, 2024
Abs PDF