Core Deep Learning

Deep learning being now a key component of AD systems, it is important to get a better understanding of its inner workings, in particular the link between the specifics of the learning optimization and the key properities (performance, regularity, robustness, generalization) of the trained models. Among other things, we investigate the impact of popular batch normalization on standard learning procedures and the ability to learn through unsupervised distillation.

Publications

QuEST: Quantized Embedding Space for Transferring Knowledge

Himalaya Jain, Spyros Gidaris, Nikos Komodakis, Patrick PĂ©rez, and Matthieu Cord
European Conference on Computer Vision (ECCV), 2020