Sebastien Piat

Papers

Total Citations

H-Index

About

Sebastien Piat is a researcher at the forefront of quantum machine learning and computer vision, whose work explores the intersection of these transformative fields. His most-cited paper, "Image classification with quantum pre-training and auto-encoders" (2018, 16 citations), addresses a critical challenge: how to process images on near-term quantum devices. Piat pioneered a hybrid approach that uses classical auto-encoders to compress image data before feeding it into quantum circuits for pre-training, demonstrating that quantum-enhanced feature extraction can improve classification accuracy even on today's limited hardware. This work has become a foundational reference for researchers seeking practical quantum advantages in computer vision, from medical imaging to robotics. Beyond this landmark study, Piat's research consistently bridges theoretical quantum algorithms with real-world applications, making him a key voice in the growing dialogue between quantum computing and AI. His contributions help chart a viable path toward quantum-enhanced machine learning, inspiring a new generation of researchers to explore how noisy intermediate-scale quantum devices can tackle complex visual tasks.