Get started
Author

Puneet K. Dokania

Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
2018 · Arslan Chaudhry, Puneet K. Dokania, et al. · Lecture notes in computer science · 1,092
PDF
GDumb: A Simple Approach that Questions Our Progress in Continual Learning
2020 · Ameya Prabhu, Philip H. S. Torr, et al. · Lecture notes in computer science · 499
On Tiny Episodic Memories in Continual Learning
2019 · Chaudhry, Arslan, Rohrbach, Marcus, et al. · arXiv (Cornell University) · 348
PDF
Multi-agent Diverse Generative Adversarial Networks
2018 · Arnab Ghosh, Viveka Kulharia, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 306
PDF
Calibrating Deep Neural Networks using Focal Loss
2020 · Mukhoti, Jishnu, Kulharia, Viveka, et al. · arXiv (Cornell University) · 227
PDF
Continual learning with tiny episodic memories
2019 · Arslan Chaudhry, Marcus Rohrbach, et al. · arXiv (Cornell University) · 214
Using Hindsight to Anchor Past Knowledge in Continual Learning
2021 · Arslan Chaudhry, Albert Gordo, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 200
Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation
2017 · Arslan Chaudhry, Puneet Kumar Dokania, et al. · British Machine Vision Conference (BMVC) · 144
PDF
Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation
2019 · Arnab Ghosh, Richard Zhang, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 116
Continual Learning in Low-rank Orthogonal Subspaces
2020 · Chaudhry, Arslan, Khan, Naeemullah, et al. · arXiv (Cornell University) · 54
PDF
An Impartial Take to the CNN vs Transformer Robustness Contest
2022 · Francesco Pinto, Philip H. S. Torr, et al. · Lecture notes in computer science · 52
PDF
Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs
2016 · Osokin, Anton, Alayrac, Jean-Baptiste, et al. · HAL · 44
PDF
Progressive Skeletonization: Trimming more fat from a network at initialization
2020 · de Jorge, Pau, Sanyal, Amartya, et al. · arXiv (Cornell University) · 42
PDF
Computationally Budgeted Continual Learning: What Does Matter?
2023 · Ameya Prabhu, Hasan Abed Al Kader Hammoud, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 41
PDF
Bottom-Up Top-Down Cues for Weakly-Supervised Semantic Segmentation
2018 · Qibin Hou, Daniela Massiceti, et al. · Lecture notes in computer science · 37
PDF
Sample-Dependent Adaptive Temperature Scaling for Improved Calibration
2023 · Tom Joy, Francesco Pinto, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 35
PDF
FLIPDIAL: A Generative Model for Two-Way Visual Dialogue
2018 · Puneet K. Dokania, Philip H.S. Torr, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 33
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training
2022 · de Jorge, Pau, Bibi, Adel, et al. · arXiv (Cornell University) · 31
PDF
Stable Rank Normalization for Improved Generalization in Neural Networks and GANs
2019 · Sanyal, Amartya, Torr, Philip H. S., et al. · arXiv (Cornell University) · 29
PDF
Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration
2023 · Kemal Oksuz, Tom Joy, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 25
PDF
FlipDial: A Generative Model for Two-Way Visual Dialogue
2018 · Massiceti, Daniela, Siddharth, N., et al. · arXiv (Cornell University) · 22
PDF
Graph Inductive Biases in Transformers without Message Passing
2023 · Ma, Liheng, Lin, Chen, et al. · arXiv (Cornell University) · 21
PDF
Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation
2019 · Ghosh, Arnab, Zhang, Richard, et al. · arXiv (Cornell University) · 21
PDF
Deformable Registration Through Learning of Context-Specific Metric Aggregation
2017 · Enzo Ferrante, Puneet K. Dokania, et al. · Lecture notes in computer science · 21
Visual Dialogue without Vision or Dialogue
2018 · Massiceti, Daniela, Dokania, Puneet K., et al. · arXiv (Cornell University) · 18
PDF
Works count: 80
Citation count: 3,877
H-index: 21
I10-index: 32
Year
Topic
Type