Puneet K. Dokania

According to our database, Puneet K. Dokania authored at least 55 papers between 2014 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Fine-tuning can cripple your foundation model; preserving features may be the solution.

Jishnu Mukhoti, Yarin Gal, Philip Torr, Puneet K. Dokania

Trans. Mach. Learn. Res., 2024

What Makes and Breaks Safety Fine-tuning? A Mechanistic Study.

Samyak Jain, Ekdeep Singh Lubana, Kemal Oksuz, Tom Joy, Philip H. S. Torr, Amartya Sanyal, Puneet K. Dokania

CoRR, 2024

RanDumb: A Simple Approach that Questions the Efficacy of Continual Representation Learning.

Ameya Prabhu, Shiven Sinha, Ponnurangam Kumaraguru, Philip H. S. Torr, Ozan Sener, Puneet K. Dokania

CoRR, 2024

On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines.

Selim Kuzucu, Kemal Oksuz, Jonathan Sadeghi, Puneet K. Dokania

Proceedings of the Computer Vision - ECCV 2024, 2024

Placing Objects in Context via Inpainting for Out-of-Distribution Segmentation.

Pau de Jorge, Riccardo Volpi, Puneet K. Dokania, Philip H. S. Torr, Grégory Rogez

Proceedings of the Computer Vision - ECCV 2024, 2024

2023

Catastrophic overfitting can be induced with discriminative non-robust features.

Guillermo Ortiz-Jiménez, Pau de Jorge, Amartya Sanyal, Adel Bibi, Puneet K. Dokania, Pascal Frossard, Grégory Rogez, Philip Torr

Trans. Mach. Learn. Res., 2023

Diagnosing and Preventing Instabilities in Recurrent Video Processing.

Thomas Tanay, Aivar Sootla, Matteo Maggioni, Puneet K. Dokania, Philip H. S. Torr, Ales Leonardis, Gregory G. Slabaugh

IEEE Trans. Pattern Anal. Mach. Intell., 2023

Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation.

Francisco Eiras, Kemal Oksuz, Adel Bibi, Philip H. S. Torr, Puneet K. Dokania

CoRR, 2023

MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection.

Kemal Oksuz, Selim Kuzucu, Tom Joy, Puneet K. Dokania

CoRR, 2023

Online Continual Learning Without the Storage Constraint.

Ameya Prabhu, Zhipeng Cai, Puneet K. Dokania, Philip H. S. Torr, Vladlen Koltun, Ozan Sener

CoRR, 2023

Graph Inductive Biases in Transformers without Message Passing.

Liheng Ma, Chen Lin, Derek Lim, Adriana Romero-Soriano, Puneet K. Dokania, Mark Coates, Philip H. S. Torr, Ser-Nam Lim

Proceedings of the International Conference on Machine Learning, 2023

Raising the Bar on the Evaluation of Out-of-Distribution Detection.

Jishnu Mukhoti, Tsung-Yu Lin, Bor-Chun Chen, Ashish Shah, Philip H. S. Torr, Puneet K. Dokania, Ser-Nam Lim

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Computationally Budgeted Continual Learning: What Does Matter?

Ameya Prabhu, Hasan Abed Al Kader Hammoud, Puneet K. Dokania, Philip H. S. Torr, Ser-Nam Lim, Bernard Ghanem, Adel Bibi

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration.

Kemal Oksuz, Tom Joy, Puneet K. Dokania

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Sample-Dependent Adaptive Temperature Scaling for Improved Calibration.

Tom Joy, Francesco Pinto, Ser-Nam Lim, Philip H. S. Torr, Puneet K. Dokania

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

Query-Based Hard-Image Retrieval for Object Detection at Test Time.

Edward Ayers, Jonathan Sadeghi, John Redford, Romain Mueller, Puneet K. Dokania

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022

ANCER: Anisotropic Certification via Sample-wise Volume Maximization.

Francisco Eiras, Motasem Alfarra, Philip H. S. Torr, M. Pawan Kumar, Puneet K. Dokania, Bernard Ghanem, Adel Bibi

Trans. Mach. Learn. Res., 2022

RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness.

Francesco Pinto, Harry Yang, Ser-Nam Lim, Philip H. S. Torr, Puneet K. Dokania

CoRR, 2022

Catastrophic overfitting is a bug but also a feature.

Guillermo Ortiz-Jiménez, Pau de Jorge, Amartya Sanyal, Adel Bibi, Puneet K. Dokania, Pascal Frossard, Grégory Rogez, Philip H. S. Torr

CoRR, 2022

Using Mixup as a Regularizer Can Surprisingly Improve Accuracy & Out-of-Distribution Robustness.

Francesco Pinto, Harry Yang, Ser Nam Lim, Philip H. S. Torr, Puneet K. Dokania

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Make Some Noise: Reliable and Efficient Single-Step Adversarial Training.

Pau de Jorge Aranda, Adel Bibi, Riccardo Volpi, Amartya Sanyal, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

An Impartial Take to the CNN vs Transformer Robustness Contest.

Francesco Pinto, Philip H. S. Torr, Puneet K. Dokania

Proceedings of the Computer Vision - ECCV 2022, 2022

2021

A Step Towards Efficient Evaluation of Complex Perception Tasks in Simulation.

Jonathan Sadeghi, Blaine Rogers, James Gunn, Thomas Saunders, Sina Samangooei, Puneet Kumar Dokania, John Redford

CoRR, 2021

Multilevel Knowledge Transfer for Cross-Domain Object Detection.

Botos Csaba, Xiaojuan Qi, Arslan Chaudhry, Puneet K. Dokania, Philip H. S. Torr

CoRR, 2021

A Continuous Mapping For Augmentation Design.

Keyu Tian, Chen Lin, Ser-Nam Lim, Wanli Ouyang, Puneet K. Dokania, Philip H. S. Torr

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

How Benign is Benign Overfitting ?

Amartya Sanyal, Puneet K. Dokania, Varun Kanade, Philip H. S. Torr

Proceedings of the 9th International Conference on Learning Representations, 2021

No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks.

Shyamgopal Karthik, Ameya Prabhu, Puneet K. Dokania, Vineet Gandhi

Proceedings of the 9th International Conference on Learning Representations, 2021

Progressive Skeletonization: Trimming more fat from a network at initialization.

Pau de Jorge, Amartya Sanyal, Harkirat S. Behl, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania

Proceedings of the 9th International Conference on Learning Representations, 2021

Mirror Descent View for Neural Network Quantization.

Thalaiyasingam Ajanthan, Kartik Gupta, Philip H. S. Torr, Richard Hartley, Puneet K. Dokania

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

Using Hindsight to Anchor Past Knowledge in Continual Learning.

Arslan Chaudhry, Albert Gordo, Puneet K. Dokania, Philip H. S. Torr, David Lopez-Paz

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020

On Batch Normalisation for Approximate Bayesian Inference.

Jishnu Mukhoti, Puneet K. Dokania, Philip H. S. Torr, Yarin Gal

CoRR, 2020

Simulation-Based Inference for Global Health Decisions.

Christian Schröder de Witt, Bradley Gram-Hansen, Nantas Nardelli, Andrew Gambardella, Robert Zinkov, Puneet K. Dokania, N. Siddharth, Ana Belen Espinosa-Gonzalez, Ara Darzi, Philip H. S. Torr, Atilim Günes Baydin

CoRR, 2020

A Revised Generative Evaluation of Visual Dialogue.

Daniela Massiceti, Viveka Kulharia, Puneet K. Dokania, N. Siddharth, Philip H. S. Torr

CoRR, 2020

Calibrating Deep Neural Networks using Focal Loss.

Jishnu Mukhoti, Viveka Kulharia, Amartya Sanyal, Stuart Golodetz, Philip H. S. Torr, Puneet K. Dokania

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Continual Learning in Low-rank Orthogonal Subspaces.

Arslan Chaudhry, Naeemullah Khan, Puneet K. Dokania, Philip H. S. Torr

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Stable Rank Normalization for Improved Generalization in Neural Networks and GANs.

Amartya Sanyal, Philip H. S. Torr, Puneet K. Dokania

Proceedings of the 8th International Conference on Learning Representations, 2020

GDumb: A Simple Approach that Questions Our Progress in Continual Learning.

Ameya Prabhu, Philip H. S. Torr, Puneet K. Dokania

Proceedings of the Computer Vision - ECCV 2020, 2020

2019

Weakly Supervised Learning of Metric Aggregations for Deformable Image Registration.

Enzo Ferrante, Puneet Kumar Dokania, Rafael Marini, Nikos Paragios

IEEE J. Biomed. Health Informatics, 2019

Continual Learning with Tiny Episodic Memories.

Arslan Chaudhry, Marcus Rohrbach, Mohamed Elhoseiny, Thalaiyasingam Ajanthan, Puneet Kumar Dokania, Philip H. S. Torr, Marc'Aurelio Ranzato

CoRR, 2019

Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation.

Arnab Ghosh, Richard Zhang, Puneet K. Dokania, Oliver Wang, Alexei A. Efros, Philip H. S. Torr, Eli Shechtman

Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Proximal Mean-Field for Neural Network Quantization.

Thalaiyasingam Ajanthan, Puneet K. Dokania, Richard Hartley, Philip H. S. Torr

Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

2018

Visual Dialogue without Vision or Dialogue.

Daniela Massiceti, Puneet K. Dokania, N. Siddharth, Philip H. S. Torr

CoRR, 2018

Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence.

Arslan Chaudhry, Puneet Kumar Dokania, Thalaiyasingam Ajanthan, Philip H. S. Torr

Proceedings of the Computer Vision - ECCV 2018, 2018

FlipDial: A Generative Model for Two-Way Visual Dialogue.

Daniela Massiceti, N. Siddharth, Puneet Kumar Dokania, Philip H. S. Torr

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Multi-Agent Diverse Generative Adversarial Networks.

Arnab Ghosh, Viveka Kulharia, Vinay P. Namboodiri, Philip H. S. Torr, Puneet Kumar Dokania

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

2017

Deformable Registration Through Learning of Context-Specific Metric Aggregation.

Enzo Ferrante, Puneet Kumar Dokania, Rafael Marini, Nikos Paragios

Proceedings of the Machine Learning in Medical Imaging - 8th International Workshop, 2017

Bottom-Up Top-Down Cues for Weakly-Supervised Semantic Segmentation.

Qibin Hou, Daniela Massiceti, Puneet Kumar Dokania, Yunchao Wei, Ming-Ming Cheng, Philip H. S. Torr

Proceedings of the Energy Minimization Methods in Computer Vision and Pattern Recognition, 2017

Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation.

Arslan Chaudhry, Puneet Kumar Dokania, Philip H. S. Torr

Proceedings of the British Machine Vision Conference 2017, 2017

2016

High-Order Inference, Ranking, and Regularization Path for Structured SVM. (Inférence d'ordre supérieur, Classement, et Chemin de Régularisation pour les SVM Structurés).

Puneet Kumar Dokania

PhD thesis, 2016

Rounding-based Moves for Semi-Metric Labeling.

M. Pawan Kumar, Puneet Kumar Dokania

J. Mach. Learn. Res., 2016

Mining Pixels: Weakly Supervised Semantic Segmentation Using Image Labels.

Qinbin Hou, Puneet Kumar Dokania, Daniela Massiceti, Yunchao Wei, Ming-Ming Cheng, Philip H. S. Torr

CoRR, 2016

Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs.

Anton Osokin, Jean-Baptiste Alayrac, Isabella Lukasewitz, Puneet Kumar Dokania, Simon Lacoste-Julien

Proceedings of the 33nd International Conference on Machine Learning, 2016

Partial Linearization Based Optimization for Multi-class SVM.

Pritish Mohapatra, Puneet Kumar Dokania, C. V. Jawahar, M. Pawan Kumar

Proceedings of the Computer Vision - ECCV 2016, 2016

2015

Parsimonious Labeling.

Puneet Kumar Dokania, M. Pawan Kumar

Proceedings of the 2015 IEEE International Conference on Computer Vision, 2015

2014

Learning to Rank Using High-Order Information.

Puneet Kumar Dokania, Aseem Behl, C. V. Jawahar, M. Pawan Kumar

Proceedings of the Computer Vision - ECCV 2014, 2014