Angelos Katharopoulos
Angelos Katharopoulos
Idiap and EPFL
Verified email at idiap.ch - Homepage
Title
Cited by
Cited by
Year
Not all samples are created equal: Deep learning with importance sampling
A Katharopoulos, F Fleuret
International Conference on Machine Learning (ICML), 2018
1512018
Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
A Katharopoulos, A Vyas, N Pappas, F Fleuret
International Conference on Machine Learning (ICML), 2020
832020
Biased importance sampling for deep neural network training
A Katharopoulos, F Fleuret
arXiv preprint arXiv:1706.00043, 2017
362017
Processing megapixel images with deep attention-sampling models
A Katharopoulos, F Fleuret
International Conference on Machine Learning (ICML), 2019
212019
Fast transformers with clustered attention
A Vyas, A Katharopoulos, F Fleuret
Neural Information Processing Systems (NeurIPS), 2020
172020
Fast supervised LDA for discovering micro-events in large-scale video datasets
A Katharopoulos, D Paschalidou, C Diou, A Delopoulos
Proceedings of the 24th ACM international conference on Multimedia, 332-336, 2016
42016
Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks
D Paschalidou, A Katharopoulos, A Geiger, S Fidler
Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2021, 2021
12021
Learning local feature aggregation functions with backpropagation
A Katharopoulos, D Paschalidou, C Diou, A Delopoulos
2017 25th European Signal Processing Conference (EUSIPCO), 748-752, 2017
12017
Supplementary Material for Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks.
D Paschalidou, A Katharopoulos, A Geiger, S Fidler
Not All Samples Are Created Equal Supplementary material
A Katharopoulos, F Fleuret
The system can't perform the operation now. Try again later.
Articles 1–10