Sotabase

Career

· Research Director, Five AI2019–
· Senior Researcher, University of Oxford2019–
· PhD Student, INRIA and CentraleSupélec2012–

Publications (66)

Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
European Conference on Computer Vision · 2018
1,316
cited
On Tiny Episodic Memories in Continual Learning
2019
787
cited
GDumb: A Simple Approach that Questions Our Progress in Continual Learning
European Conference on Computer Vision · 2020
694
cited
Calibrating Deep Neural Networks using Focal Loss
Neural Information Processing Systems · 2020
576
cited
Continual Learning with Tiny Episodic Memories
arXiv.org · 2019
453
cited
Multi-agent Diverse Generative Adversarial Networks
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2017
324
cited
Using Hindsight to Anchor Past Knowledge in Continual Learning
AAAI Conference on Artificial Intelligence · 2019
269
cited
Graph Inductive Biases in Transformers without Message Passing
International Conference on Machine Learning · 2023
159
cited
Continual Learning in Low-rank Orthogonal Subspaces
Neural Information Processing Systems · 2020
152
cited
Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation
IEEE International Conference on Computer Vision · 2019
143
cited
Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation
British Machine Vision Conference · 2017
124
cited
Progressive Skeletonization: Trimming more fat from a network at initialization
International Conference on Learning Representations · 2020
108
cited
Computationally Budgeted Continual Learning: What Does Matter?
Computer Vision and Pattern Recognition · 2023
79
cited
Fine-tuning can cripple your foundation model; preserving features may be the solution
Trans. Mach. Learn. Res. · 2023
75
cited
Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs
International Conference on Machine Learning · 2016
68
cited
Using Mixup as a Regularizer Can Surprisingly Improve Accuracy & Out-of-Distribution Robustness
Neural Information Processing Systems · 2022
63
cited
How benign is benign overfitting?
International Conference on Learning Representations · 2020
61
cited
An Impartial Take to the CNN vs Transformer Robustness Contest
European Conference on Computer Vision · 2022
60
cited
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training
Neural Information Processing Systems · 2022
58
cited
Stable Rank Normalization for Improved Generalization in Neural Networks and GANs
International Conference on Learning Representations · 2019
54
cited
Sotabase
Puneet Kumar Dokania | Researcher Profile | Sotabase | Sotabase