Follow
Amal Rannen Triki
Amal Rannen Triki
Research Scientist at Google DeepMind
Verified email at google.com - Homepage
Title
Cited by
Cited by
Year
The Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks
M Berman, A Rannen Triki, MB Blaschko
8692018
Encoder based lifelong learning
A Rannen-Triki*, R Aljundi*, MB Blaschko, ...
Proceedings of the IEEE International Conference on Computer Vision, 1320-1328, 2017
3442017
A Bayesian optimization framework for neural network compression
X Ma*, A Rannen-Triki*, M Berman, C Sagonas, J Cali, ...
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2019
252019
Intraoperative margin assessment of human breast tissue in optical coherence tomography images using deep neural networks
AR Triki, MB Blaschko, YM Jung, S Song, HJ Han, SI Kim, C Joo
Computerized Medical Imaging and Graphics 69, 21-32, 2018
202018
Function norms for neural networks
A Rannen-Triki, M Berman, V Kolmogorov, MB Blaschko
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2019
12*2019
On the role of optimization in double descent: A least squares study
I Kuzborskij, C Szepesvári, O Rivasplata, A Rannen-Triki, R Pascanu
Advances in Neural Information Processing Systems 34, 29567-29577, 2021
102021
NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research
J Bornschein*, A Galashov*, R Hemsley*, A Rannen-Triki*, Y Chen, ...
arXiv preprint arXiv:2211.11747, 2022
82022
The Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks. arXiv 2017
M Berman, AR Triki, MB Blaschko
arXiv preprint arXiv:1705.08790, 0
6
Towards better visual explanations for deep image classifiers
A Grabska-Barwinska, A Rannen-Triki, O Rivasplata, A György
eXplainable AI approaches for debugging and diagnosis., 2021
22021
Encoder Based Lifelong Learning.
A Rannen-Triki*, R Aljundi*, MB Blaschko, ...
CoRR, 2017
22017
Revisiting evaluation metrics for semantic segmentation: Optimization and evaluation of fine-grained intersection over union
Z Wang, M Berman, A Rannen-Triki, P Torr, D Tuia, T Tuytelaars, LV Gool, ...
Advances in Neural Information Processing Systems 36, 2024
12024
Towards robust and efficient continual language learning
A Fisch, A Rannen-Triki, R Pascanu, J Bornschein, A Lazaridou, ...
arXiv preprint arXiv:2307.05741, 2023
12023
Kalman Filter for Online Classification of Non-Stationary Data
MK Titsias, A Galashov, A Rannen-Triki, R Pascanu, YW Teh, ...
arXiv preprint arXiv:2306.08448, 2023
12023
Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models
A Rannen-Triki, J Bornschein, R Pascanu, A Galashov, M Titsias, M Hutter, ...
NeurIPS 2023 Workshop on Distribution Shifts: New Frontiers with Foundation …, 2023
2023
Kalman Filter Online Learning from non-Stationary Data
M Titsias, A Galashov, A Rannen-Triki, R Pascanu, YW Teh, J Bornschein
The Twelfth International Conference on Learning Representations, 2023
2023
Towards Compute-Optimal Transfer Learning
M Caccia, A Galashov, A Douillard, A Rannen-Triki, D Rao, M Paganini, ...
arXiv preprint arXiv:2304.13164, 2023
2023
Function Norms for Neural Networks: Theory and Applications
A Rannen Ep Triki
2020
Yes, IoU loss is submodular-as a function of the mispredictions
M Berman, MB Blaschko, AR Triki, J Yu
arXiv preprint arXiv:1809.01845, 2018
2018
The system can't perform the operation now. Try again later.
Articles 1–18