Jean-Baptiste Cordonnier
6 papers · 2018–2021 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(20)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Deep Learning
(5)
Machine Learning
(5)
Architectures
(4)
Optimization & Theory · Machine Learning
(3)
Computer Vision
(2)
Core AI · Computer Vision
(2)
Core Methods
(2)
Techniques
(2)
Artificial Intelligence
(1)
Mathematics & Optimization
(1)
Application Areas
(1)
Core AI · Artificial Intelligence
(1)
Learning Types
(1)
Optimization
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
self-attention network
(2)
stochastic gradient descent
(1)
vision transformer
(1)
attention mechanism
(1)
trajectory prediction
(1)
distributed optimization
(1)
neural network optimization
(1)
theoretical analysis
(1)
communication efficiency
(1)
image recognition
(1)
fine-grained recognition
(1)
gradient compression
(1)
inductive bia
(1)
node embedding
(1)
communication compression
(1)
positional encoding
(1)
end-to-end training
(1)
group equivariance
(1)
skip connection
(1)
error compensation
(1)
Papers
Attention is not all you need: pure attention loses rank doubly exponentially with depth
ICML 2021
Differentiable Patch Selection for Image Recognition
CVPR 2021
Group Equivariant Stand-Alone Self-Attention For Vision
ICLR 2021
On the Relationship between Self-Attention and Convolutional Layers
ICLR 2020
Extrapolating Paths with Graph Neural Networks
IJCAI 2019
Sparsified SGD with Memory
NeurIPS 2018