Prati
Puneet K. Dokania
Puneet K. Dokania
University of Oxford | Bosch (Five AI)
Potvrđena adresa e-pošte na robots.ox.ac.uk - Početna stranica
Naslov
Citirano
Citirano
Godina
Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
A Chaudhry*, PK Dokania*, T Ajanthan*, PHS Torr
In ECCV (2018), 2018
14162018
Continual learning with tiny episodic memories
A Chaudhry, M Rohrbach, M Elhoseiny, T Ajanthan, PK Dokania, ...
In ICML 2019 Workshop on Multi-Task and Lifelong Reinforcement Learning, 2019
1064*2019
GDumb: A Simple Approach that Questions Our Progress in Continual Learning
A Prabhu, PHS Torr, PK Dokania
In ECCV 2020, 2020
6982020
Calibrating Deep Neural Networks using Focal Loss
J Mukhoti, V Kulharia, A Sanyal, S Golodetz, PHS Torr, PK Dokania
In NeurIPS 2020, 2020
5562020
Learning-based approach for online lane change intention prediction
P Kumar, M Perrollaz, S Lefevre, C Laugier
2013 IEEE Intelligent Vehicles Symposium (IV), 797-802, 2013
5122013
Multi-Agent Diverse Generative Adversarial Networks
A Ghosh, V Kulharia, V Namboodiri, PHS Torr, PK Dokania
In CVPR (2018), 2017
4182017
Using hindsight to anchor past knowledge in continual learning
A Chaudhry, A Gordo, PK Dokania, P Torr, D Lopez-Paz
In AAAI 2021, 2021
2672021
Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation
A Chaudhry, PK Dokania, PHS Torr
British Machine Vision Conference (BMVC 2017), 2017
1652017
Interactive sketch & fill: Multiclass sketch-to-image translation
A Ghosh, R Zhang, PK Dokania, O Wang, AA Efros, PHS Torr, ...
In ICCV (2019), 1171-1180, 2019
1632019
Continual Learning in Low-rank Orthogonal Subspaces
A Chaudhry, N Khan, PK Dokania, PHS Torr
In NeurIPS 2020, 2020
1432020
Progressive skeletonization: Trimming more fat from a network at initialization
P de Jorge, A Sanyal, HS Behl, PHS Torr, G Rogez, PK Dokania
In ICLR 2021, 2021
1172021
Graph Inductive Biases in Transformers without Message Passing
L Ma, C Lin, D Lim, A Romero-Soriano, PK Dokania, M Coates, P Torr, ...
In ICML 2023, 2023
1142023
RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness
F Pinto, H Yang, SN Lim, PHS Torr, PK Dokania
Neural Information Processing Systems (NeurIPS) 2022, 2022
103*2022
A novel bacterial foraging technique for edge detection
OP Verma, M Hanmandlu, P Kumar, S Chhabra, A Jindal
Pattern recognition letters 32 (8), 1187-1196, 2011
1022011
High dynamic range optimal fuzzy color image enhancement using artificial ant colony system
OP Verma, P Kumar, M Hanmandlu, S Chhabra
Applied Soft Computing 12 (1), 394-404, 2012
932012
Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs
A Osokin, JB Alayrac, I Lukasewitz, PK Dokania, S Lacoste-Julien
In ICML (2016), 2016
892016
How benign is benign overfitting?
A Sanyal, PK Dokania, V Kanade, PHS Torr
In ICLR 2021, 2021
732021
Computationally Budgeted Continual Learning: What Does Matter?
A Prabhu, HAAK Hammoud, P Dokania, PHS Torr, SN Lim, B Ghanem, ...
In CVPR 2023, 2023
712023
An Impartial Take to the CNN vs Transformer Robustness Contest
F Pinto, PHS Torr, PK Dokania
In The European Conference on Computer Vision (ECCV) 2022, 2022
70*2022
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training
P de Jorge, A Bibi, R Volpi, A Sanyal, PHS Torr, G Rogez, PK Dokania
Neural Information Processing Systems (NeurIPS) 2022, 2022
63*2022
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20