Jean-Baptiste Cordonnier
Jean-Baptiste Cordonnier
PhD Student, EPFL
Verified email at epfl.ch - Homepage
Title
Cited by
Cited by
Year
Sparsified SGD with memory
SU Stich, JB Cordonnier, M Jaggi
NeurIPS 2018, 4447-4458, 2018
2982018
On the Relationship between Self-Attention and Convolutional Layers
JB Cordonnier, A Loukas, M Jaggi
ICLR 2020, 2019
1252019
Attention is not all you need: Pure attention loses rank doubly exponentially with depth
Y Dong, JB Cordonnier, A Loukas
ICML 2021, 2021
192021
Group Equivariant Stand-Alone Self-Attention For Vision
DW Romero, JB Cordonnier
ICLR 2021, 2020
112020
Convex optimization using sparsified stochastic gradient descent with memory
JB Cordonnier
EPFL Master Thesis, 2018
102018
Multi-head attention: Collaborate instead of concatenate
JB Cordonnier, A Loukas, M Jaggi
arXiv preprint arXiv:2006.16362, 2020
52020
Extrapolating paths with graph neural networks
JB Cordonnier, A Loukas
IJCAI 2019, 2019
52019
On the relationship between self-attention and convolutional layers. arXiv
JB Cordonnier, A Loukas, M Jaggi
arXiv preprint arXiv:1911.03584, 2019
52019
Differentiable Patch Selection for Image Recognition
JB Cordonnier, A Mahendran, A Dosovitskiy, D Weissenborn, J Uszkoreit, ...
CVPR 2021, 2021
42021
Robust Cross-lingual Embeddings from Parallel Sentences
A Sabet, P Gupta, JB Cordonnier, R West, M Jaggi
arXiv preprint arXiv:1912.12481, 2019
42019
The system can't perform the operation now. Try again later.
Articles 1–10