Puneet K. Dokania

73 papers A* 20A 1Journal 45Unranked 7

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Foundation Models for Trajectory Planning in Autonomous Driving: A Review of Progress and Open Challenges. Trans. Mach. Learn. Res. Kemal Oksuz, Alexandru Buburuzan, Anthony Knittel, Yuhan Yao, Puneet K. Dokania
2025	J	`jnl`	AnnoCaseLaw: A Richly-Annotated Dataset For Benchmarking Explainable Legal Judgment Prediction. CoRR Magnus Sesodia, Alina Petrova, John Armour, Thomas Lukasiewicz, Oana-Maria Camburu, Puneet K. Dokania, Philip Torr, Christian Schröder de Witt
2025	J	`jnl`	Foundation Models for Trajectory Planning in Autonomous Driving: A Review of Progress and Open Challenges. CoRR Kemal Oksuz, Alexandru Buburuzan, Anthony Knittel, Yuhan Yao, Puneet K. Dokania
2025	—	`conf`	MObI: Multimodal Object Inpainting Using Diffusion Models. CVPR Workshops Alexandru Buburuzan, Anuj Sharma, John Redford, Puneet K. Dokania, Romain Mueller
2025	J	`jnl`	MObI: Multimodal Object Inpainting Using Diffusion Models. CoRR Alexandru Buburuzan, Anuj Sharma, John Redford, Puneet K. Dokania, Romain Mueller
2025	A*	`conf`	Mixture of Experts Made Intrinsically Interpretable. ICML Xingyi Yang, Constantin Venhoff, Ashkan Khakzar, Christian Schröder de Witt, Puneet K. Dokania, Adel Bibi, Philip Torr
2025	J	`jnl`	Mixture of Experts Made Intrinsically Interpretable. CoRR Xingyi Yang, Constantin Venhoff, Ashkan Khakzar, Christian Schröder de Witt, Puneet K. Dokania, Adel Bibi, Philip Torr
2025	J	`jnl`	Modeling Gene Expression Distributional Shifts for Unseen Genetic Perturbations. CoRR Kalyan Ramakrishnan, Jonathan G. Hedley, Sisi Qu, Puneet K. Dokania, Philip H. S. Torr, Cesar A. Prada-Medina, Julien Fauqueur, Kaspar Märtens
2024	J	`jnl`	Fine-tuning can cripple your foundation model; preserving features may be the solution. Trans. Mach. Learn. Res. Jishnu Mukhoti, Yarin Gal, Philip Torr, Puneet K. Dokania
2024	J	`jnl`	MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection. Trans. Mach. Learn. Res. Kemal Oksuz, Selim Kuzucu, Tom Joy, Puneet K. Dokania
2024	—	`conf`	On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines. ECCV (21) Selim Kuzucu, Kemal Oksuz, Jonathan Sadeghi, Puneet K. Dokania
2024	J	`jnl`	On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines. CoRR Selim Kuzucu, Kemal Oksuz, Jonathan Sadeghi, Puneet K. Dokania
2024	—	`conf`	Placing Objects in Context via Inpainting for Out-of-Distribution Segmentation. ECCV (45) Pau de Jorge, Riccardo Volpi, Puneet K. Dokania, Philip H. S. Torr, Grégory Rogez
2024	J	`jnl`	Placing Objects in Context via Inpainting for Out-of-distribution Segmentation. CoRR Pau de Jorge, Riccardo Volpi, Puneet K. Dokania, Philip H. S. Torr, Grégory Rogez
2024	J	`jnl`	RanDumb: A Simple Approach that Questions the Efficacy of Continual Representation Learning. CoRR Ameya Prabhu, Shiven Sinha, Ponnurangam Kumaraguru, Philip H. S. Torr, Ozan Sener, Puneet K. Dokania
2024	A*	`conf`	RanDumb: Random Representations Outperform Online Continually Learned Representations. NeurIPS Ameya Prabhu, Shiven Sinha, Ponnurangam Kumaraguru, Philip Torr, Ozan Sener, Puneet K. Dokania
2024	—	`conf`	Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation. ECCV Workshops (10) Francisco Eiras, Kemal Oksuz, Adel Bibi, Philip H. S. Torr, Puneet K. Dokania
2024	A*	`conf`	What Makes and Breaks Safety Fine-tuning? A Mechanistic Study. NeurIPS Samyak Jain, Ekdeep Singh Lubana, Kemal Oksuz, Tom Joy, Philip Torr, Amartya Sanyal, Puneet K. Dokania
2024	J	`jnl`	What Makes and Breaks Safety Fine-tuning? A Mechanistic Study. CoRR Samyak Jain, Ekdeep Singh Lubana, Kemal Oksuz, Tom Joy, Philip H. S. Torr, Amartya Sanyal, Puneet K. Dokania
2023	J	`jnl`	Catastrophic overfitting can be induced with discriminative non-robust features. Trans. Mach. Learn. Res. Guillermo Ortiz-Jiménez, Pau de Jorge, Amartya Sanyal, Adel Bibi, Puneet K. Dokania, Pascal Frossard, Grégory Rogez, Philip Torr
2023	A*	`conf`	Computationally Budgeted Continual Learning: What Does Matter? CVPR Ameya Prabhu, Hasan Abed Al Kader Hammoud, Puneet K. Dokania, Philip H. S. Torr, Ser-Nam Lim, Bernard Ghanem, Adel Bibi
2023	J	`jnl`	Computationally Budgeted Continual Learning: What Does Matter? CoRR Ameya Prabhu, Hasan Abed Al Kader Hammoud, Puneet K. Dokania, Philip H. S. Torr, Ser-Nam Lim, Bernard Ghanem, Adel Bibi
2023	J	`jnl`	Diagnosing and Preventing Instabilities in Recurrent Video Processing. IEEE Trans. Pattern Anal. Mach. Intell. Thomas Tanay, Aivar Sootla, Matteo Maggioni, Puneet K. Dokania, Philip H. S. Torr, Ales Leonardis, Gregory G. Slabaugh
2023	J	`jnl`	Fine-tuning can cripple your foundation model; preserving features may be the solution. CoRR Jishnu Mukhoti, Yarin Gal, Philip H. S. Torr, Puneet K. Dokania
2023	A*	`conf`	Graph Inductive Biases in Transformers without Message Passing. ICML Liheng Ma, Chen Lin, Derek Lim, Adriana Romero-Soriano, Puneet K. Dokania, Mark Coates, Philip H. S. Torr, Ser-Nam Lim
2023	J	`jnl`	Graph Inductive Biases in Transformers without Message Passing. CoRR Liheng Ma, Chen Lin, Derek Lim, Adriana Romero-Soriano, Puneet K. Dokania, Mark Coates, Philip H. S. Torr, Ser-Nam Lim
2023	J	`jnl`	MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection. CoRR Kemal Oksuz, Selim Kuzucu, Tom Joy, Puneet K. Dokania
2023	J	`jnl`	Online Continual Learning Without the Storage Constraint. CoRR Ameya Prabhu, Zhipeng Cai, Puneet K. Dokania, Philip H. S. Torr, Vladlen Koltun, Ozan Sener
2023	A*	`conf`	Query-Based Hard-Image Retrieval for Object Detection at Test Time. AAAI Edward Ayers, Jonathan Sadeghi, John Redford, Romain Mueller, Puneet K. Dokania
2023	—	`conf`	Raising the Bar on the Evaluation of Out-of-Distribution Detection. ICCV (Workshops) Jishnu Mukhoti, Tsung-Yu Lin, Bor-Chun Chen, Ashish Shah, Philip H. S. Torr, Puneet K. Dokania, Ser-Nam Lim
2023	A*	`conf`	Sample-Dependent Adaptive Temperature Scaling for Improved Calibration. AAAI Tom Joy, Francesco Pinto, Ser-Nam Lim, Philip H. S. Torr, Puneet K. Dokania
2023	J	`jnl`	Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation. CoRR Francisco Eiras, Kemal Oksuz, Adel Bibi, Philip H. S. Torr, Puneet K. Dokania
2023	A*	`conf`	Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration. CVPR Kemal Oksuz, Tom Joy, Puneet K. Dokania
2023	J	`jnl`	Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration. CoRR Kemal Oksuz, Tom Joy, Puneet K. Dokania
2022	J	`jnl`	ANCER: Anisotropic Certification via Sample-wise Volume Maximization. Trans. Mach. Learn. Res. Francisco Eiras, Motasem Alfarra, Philip H. S. Torr, M. Pawan Kumar, Puneet K. Dokania, Bernard Ghanem, Adel Bibi
2022	—	`conf`	An Impartial Take to the CNN vs Transformer Robustness Contest. ECCV (13) Francesco Pinto, Philip H. S. Torr, Puneet K. Dokania
2022	J	`jnl`	An Impartial Take to the CNN vs Transformer Robustness Contest. CoRR Francesco Pinto, Philip H. S. Torr, Puneet K. Dokania
2022	J	`jnl`	Catastrophic overfitting is a bug but also a feature. CoRR Guillermo Ortiz-Jiménez, Pau de Jorge, Amartya Sanyal, Adel Bibi, Puneet K. Dokania, Pascal Frossard, Grégory Rogez, Philip H. S. Torr
2022	A*	`conf`	Make Some Noise: Reliable and Efficient Single-Step Adversarial Training. NeurIPS Pau de Jorge Aranda, Adel Bibi, Riccardo Volpi, Amartya Sanyal, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania
2022	J	`jnl`	Make Some Noise: Reliable and Efficient Single-Step Adversarial Training. CoRR Pau de Jorge, Adel Bibi, Riccardo Volpi, Amartya Sanyal, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania
2022	J	`jnl`	Query-based Hard-Image Retrieval for Object Detection at Test Time. CoRR Edward Ayers, Jonathan Sadeghi, John Redford, Romain Mueller, Puneet K. Dokania
2022	J	`jnl`	Raising the Bar on the Evaluation of Out-of-Distribution Detection. CoRR Jishnu Mukhoti, Tsung-Yu Lin, Bor-Chun Chen, Ashish Shah, Philip H. S. Torr, Puneet K. Dokania, Ser-Nam Lim
2022	J	`jnl`	RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness. CoRR Francesco Pinto, Harry Yang, Ser-Nam Lim, Philip H. S. Torr, Puneet K. Dokania
2022	J	`jnl`	Sample-dependent Adaptive Temperature Scaling for Improved Calibration. CoRR Tom Joy, Francesco Pinto, Ser-Nam Lim, Philip H. S. Torr, Puneet K. Dokania
2022	A*	`conf`	Using Mixup as a Regularizer Can Surprisingly Improve Accuracy & Out-of-Distribution Robustness. NeurIPS Francesco Pinto, Harry Yang, Ser Nam Lim, Philip H. S. Torr, Puneet K. Dokania
2021	A*	`conf`	A Continuous Mapping For Augmentation Design. NeurIPS Keyu Tian, Chen Lin, Ser-Nam Lim, Wanli Ouyang, Puneet K. Dokania, Philip H. S. Torr
2021	J	`jnl`	ANCER: Anisotropic Certification via Sample-wise Volume Maximization. CoRR Francisco Eiras, Motasem Alfarra, M. Pawan Kumar, Philip H. S. Torr, Puneet K. Dokania, Bernard Ghanem, Adel Bibi
2021	A*	`conf`	How Benign is Benign Overfitting ? ICLR Amartya Sanyal, Puneet K. Dokania, Varun Kanade, Philip H. S. Torr
2021	A	`conf`	Mirror Descent View for Neural Network Quantization. AISTATS Thalaiyasingam Ajanthan, Kartik Gupta, Philip H. S. Torr, Richard Hartley, Puneet K. Dokania
2021	J	`jnl`	Multilevel Knowledge Transfer for Cross-Domain Object Detection. CoRR Botos Csaba, Xiaojuan Qi, Arslan Chaudhry, Puneet K. Dokania, Philip H. S. Torr
2021	A*	`conf`	No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks. ICLR Shyamgopal Karthik, Ameya Prabhu, Puneet K. Dokania, Vineet Gandhi
2021	J	`jnl`	No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks. CoRR Shyamgopal Karthik, Ameya Prabhu, Puneet K. Dokania, Vineet Gandhi
2021	A*	`conf`	Progressive Skeletonization: Trimming more fat from a network at initialization. ICLR Pau de Jorge, Amartya Sanyal, Harkirat S. Behl, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania
2021	A*	`conf`	Using Hindsight to Anchor Past Knowledge in Continual Learning. AAAI Arslan Chaudhry, Albert Gordo, Puneet K. Dokania, Philip H. S. Torr, David Lopez-Paz
2020	J	`jnl`	A Revised Generative Evaluation of Visual Dialogue. CoRR Daniela Massiceti, Viveka Kulharia, Puneet K. Dokania, N. Siddharth, Philip H. S. Torr
2020	A*	`conf`	Calibrating Deep Neural Networks using Focal Loss. NeurIPS Jishnu Mukhoti, Viveka Kulharia, Amartya Sanyal, Stuart Golodetz, Philip H. S. Torr, Puneet K. Dokania
2020	J	`jnl`	Calibrating Deep Neural Networks using Focal Loss. CoRR Jishnu Mukhoti, Viveka Kulharia, Amartya Sanyal, Stuart Golodetz, Philip H. S. Torr, Puneet K. Dokania
2020	A*	`conf`	Continual Learning in Low-rank Orthogonal Subspaces. NeurIPS Arslan Chaudhry, Naeemullah Khan, Puneet K. Dokania, Philip H. S. Torr
2020	J	`jnl`	Continual Learning in Low-rank Orthogonal Subspaces. CoRR Arslan Chaudhry, Naeemullah Khan, Puneet K. Dokania, Philip H. S. Torr
2020	J	`jnl`	Diagnosing and Preventing Instabilities in Recurrent Video Processing. CoRR Thomas Tanay, Aivar Sootla, Matteo Maggioni, Puneet K. Dokania, Philip H. S. Torr, Ales Leonardis, Gregory G. Slabaugh
2020	—	`conf`	GDumb: A Simple Approach that Questions Our Progress in Continual Learning. ECCV (2) Ameya Prabhu, Philip H. S. Torr, Puneet K. Dokania
2020	J	`jnl`	How benign is benign overfitting? CoRR Amartya Sanyal, Puneet K. Dokania, Varun Kanade, Philip H. S. Torr
2020	J	`jnl`	On Batch Normalisation for Approximate Bayesian Inference. CoRR Jishnu Mukhoti, Puneet K. Dokania, Philip H. S. Torr, Yarin Gal
2020	J	`jnl`	Progressive Skeletonization: Trimming more fat from a network at initialization. CoRR Pau de Jorge, Amartya Sanyal, Harkirat S. Behl, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania
2020	J	`jnl`	Simulation-Based Inference for Global Health Decisions. CoRR 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
2020	A*	`conf`	Stable Rank Normalization for Improved Generalization in Neural Networks and GANs. ICLR Amartya Sanyal, Philip H. S. Torr, Puneet K. Dokania
2020	J	`jnl`	Using Hindsight to Anchor Past Knowledge in Continual Learning. CoRR Arslan Chaudhry, Albert Gordo, Puneet K. Dokania, Philip H. S. Torr, David Lopez-Paz
2019	A*	`conf`	Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation. ICCV Arnab Ghosh, Richard Zhang, Puneet K. Dokania, Oliver Wang, Alexei A. Efros, Philip H. S. Torr, Eli Shechtman
2019	J	`jnl`	Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation. CoRR Arnab Ghosh, Richard Zhang, Puneet K. Dokania, Oliver Wang, Alexei A. Efros, Philip H. S. Torr, Eli Shechtman
2019	J	`jnl`	Mirror Descent View for Neural Network Quantization. CoRR Thalaiyasingam Ajanthan, Kartik Gupta, Philip H. S. Torr, Richard Hartley, Puneet K. Dokania
2019	A*	`conf`	Proximal Mean-Field for Neural Network Quantization. ICCV Thalaiyasingam Ajanthan, Puneet K. Dokania, Richard Hartley, Philip H. S. Torr
2019	J	`jnl`	Stable Rank Normalization for Improved Generalization in Neural Networks and GANs. CoRR Amartya Sanyal, Philip H. S. Torr, Puneet K. Dokania
2018	J	`jnl`	Visual Dialogue without Vision or Dialogue. CoRR Daniela Massiceti, Puneet K. Dokania, N. Siddharth, Philip H. S. Torr