default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDPuneet K. Dokania
Puneet Kumar Dokania
Person information
- affiliation: INRIA Saclay, CentraleSupelec
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[j6]Jishnu Mukhoti, Yarin Gal, Philip Torr, Puneet K. Dokania:
Fine-tuning can cripple your foundation model; preserving features may be the solution. Trans. Mach. Learn. Res. 2024 (2024)- [i46]Ameya Prabhu, Shiven Sinha, Ponnurangam Kumaraguru, Philip H. S. Torr, Ozan Sener, Puneet K. Dokania:
RanDumb: A Simple Approach that Questions the Efficacy of Continual Representation Learning. CoRR abs/2402.08823 (2024) - [i45]Pau de Jorge, Riccardo Volpi, Puneet K. Dokania, Philip H. S. Torr, Grégory Rogez:
Placing Objects in Context via Inpainting for Out-of-distribution Segmentation. CoRR abs/2402.16392 (2024) - [i44]Selim Kuzucu
, Kemal Oksuz, Jonathan Sadeghi, Puneet K. Dokania:
On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines. CoRR abs/2405.20459 (2024) - [i43]Samyak Jain, Ekdeep Singh Lubana, Kemal Oksuz, Tom Joy, Philip H. S. Torr, Amartya Sanyal, Puneet K. Dokania:
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study. CoRR abs/2407.10264 (2024) - 2023
- [j5]Thomas Tanay, Aivar Sootla, Matteo Maggioni, Puneet K. Dokania, Philip H. S. Torr, Ales Leonardis, Gregory G. Slabaugh:
Diagnosing and Preventing Instabilities in Recurrent Video Processing. IEEE Trans. Pattern Anal. Mach. Intell. 45(2): 1594-1605 (2023) - [j4]Guillermo Ortiz-Jiménez, Pau de Jorge, Amartya Sanyal, Adel Bibi, Puneet K. Dokania, Pascal Frossard, Grégory Rogez, Philip Torr:
Catastrophic overfitting can be induced with discriminative non-robust features. Trans. Mach. Learn. Res. 2023 (2023) - [c31]Edward Ayers, Jonathan Sadeghi, John Redford, Romain Mueller, Puneet K. Dokania:
Query-Based Hard-Image Retrieval for Object Detection at Test Time. AAAI 2023: 14692-14700 - [c30]Tom Joy, Francesco Pinto, Ser-Nam Lim, Philip H. S. Torr, Puneet K. Dokania:
Sample-Dependent Adaptive Temperature Scaling for Improved Calibration. AAAI 2023: 14919-14926 - [c29]Ameya Prabhu, Hasan Abed Al Kader Hammoud, Puneet K. Dokania, Philip H. S. Torr, Ser-Nam Lim, Bernard Ghanem, Adel Bibi:
Computationally Budgeted Continual Learning: What Does Matter? CVPR 2023: 3698-3707 - [c28]Kemal Oksuz, Tom Joy, Puneet K. Dokania:
Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration. CVPR 2023: 9263-9274 - [c27]Jishnu Mukhoti, Tsung-Yu Lin, Bor-Chun Chen, Ashish Shah, Philip H. S. Torr, Puneet K. Dokania, Ser-Nam Lim:
Raising the Bar on the Evaluation of Out-of-Distribution Detection. ICCV (Workshops) 2023: 4367-4377 - [c26]Liheng Ma, Chen Lin, Derek Lim, Adriana Romero-Soriano, Puneet K. Dokania, Mark Coates, Philip H. S. Torr, Ser-Nam Lim:
Graph Inductive Biases in Transformers without Message Passing. ICML 2023: 23321-23337 - [i42]Ameya Prabhu, Hasan Abed Al Kader Hammoud, Puneet K. Dokania, Philip H. S. Torr, Ser-Nam Lim, Bernard Ghanem, Adel Bibi:
Computationally Budgeted Continual Learning: What Does Matter? CoRR abs/2303.11165 (2023) - [i41]Ameya Prabhu, Zhipeng Cai, Puneet K. Dokania, Philip H. S. Torr, Vladlen Koltun, Ozan Sener:
Online Continual Learning Without the Storage Constraint. CoRR abs/2305.09253 (2023) - [i40]Liheng Ma, Chen Lin, Derek Lim, Adriana Romero-Soriano, Puneet K. Dokania, Mark Coates, Philip H. S. Torr, Ser-Nam Lim:
Graph Inductive Biases in Transformers without Message Passing. CoRR abs/2305.17589 (2023) - [i39]Kemal Oksuz, Tom Joy, Puneet K. Dokania:
Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration. CoRR abs/2307.00934 (2023) - [i38]Jishnu Mukhoti, Yarin Gal, Philip H. S. Torr, Puneet K. Dokania:
Fine-tuning can cripple your foundation model; preserving features may be the solution. CoRR abs/2308.13320 (2023) - [i37]Kemal Oksuz, Selim Kuzucu, Tom Joy, Puneet K. Dokania:
MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection. CoRR abs/2309.14976 (2023) - [i36]Francisco Eiras, Kemal Oksuz, Adel Bibi, Philip H. S. Torr, Puneet K. Dokania:
Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation. CoRR abs/2310.13479 (2023) - 2022
- [j3]Francisco Eiras, Motasem Alfarra, Philip H. S. Torr, M. Pawan Kumar, Puneet K. Dokania, Bernard Ghanem, Adel Bibi:
ANCER: Anisotropic Certification via Sample-wise Volume Maximization. Trans. Mach. Learn. Res. 2022 (2022) - [c25]Francesco Pinto, Philip H. S. Torr, Puneet K. Dokania:
An Impartial Take to the CNN vs Transformer Robustness Contest. ECCV (13) 2022: 466-480 - [c24]Pau de Jorge Aranda, Adel Bibi, Riccardo Volpi, Amartya Sanyal, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania:
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training. NeurIPS 2022 - [c23]Francesco Pinto, Harry Yang, Ser Nam Lim, Philip H. S. Torr, Puneet K. Dokania:
Using Mixup as a Regularizer Can Surprisingly Improve Accuracy & Out-of-Distribution Robustness. NeurIPS 2022 - [i35]Pau de Jorge, Adel Bibi, Riccardo Volpi, Amartya Sanyal, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania:
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training. CoRR abs/2202.01181 (2022) - [i34]Guillermo Ortiz-Jiménez, Pau de Jorge, Amartya Sanyal, Adel Bibi, Puneet K. Dokania, Pascal Frossard, Grégory Rogez, Philip H. S. Torr:
Catastrophic overfitting is a bug but also a feature. CoRR abs/2206.08242 (2022) - [i33]Francesco Pinto, Harry Yang, Ser-Nam Lim, Philip H. S. Torr, Puneet K. Dokania:
RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness. CoRR abs/2206.14502 (2022) - [i32]Tom Joy, Francesco Pinto, Ser-Nam Lim, Philip H. S. Torr, Puneet K. Dokania:
Sample-dependent Adaptive Temperature Scaling for Improved Calibration. CoRR abs/2207.06211 (2022) - [i31]Francesco Pinto, Philip H. S. Torr, Puneet K. Dokania:
An Impartial Take to the CNN vs Transformer Robustness Contest. CoRR abs/2207.11347 (2022) - [i30]Edward Ayers, Jonathan Sadeghi, John Redford, Romain Mueller, Puneet K. Dokania:
Query-based Hard-Image Retrieval for Object Detection at Test Time. CoRR abs/2209.11559 (2022) - [i29]Jishnu Mukhoti, Tsung-Yu Lin, Bor-Chun Chen, Ashish Shah, Philip H. S. Torr, Puneet K. Dokania, Ser-Nam Lim:
Raising the Bar on the Evaluation of Out-of-Distribution Detection. CoRR abs/2209.11960 (2022) - 2021
- [c22]Arslan Chaudhry, Albert Gordo, Puneet K. Dokania, Philip H. S. Torr, David Lopez-Paz:
Using Hindsight to Anchor Past Knowledge in Continual Learning. AAAI 2021: 6993-7001 - [c21]Thalaiyasingam Ajanthan, Kartik Gupta, Philip H. S. Torr, Richard Hartley, Puneet K. Dokania:
Mirror Descent View for Neural Network Quantization. AISTATS 2021: 2809-2817 - [c20]Pau de Jorge, Amartya Sanyal, Harkirat S. Behl, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania:
Progressive Skeletonization: Trimming more fat from a network at initialization. ICLR 2021 - [c19]Shyamgopal Karthik, Ameya Prabhu, Puneet K. Dokania, Vineet Gandhi:
No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks. ICLR 2021 - [c18]Amartya Sanyal, Puneet K. Dokania, Varun Kanade, Philip H. S. Torr:
How Benign is Benign Overfitting ? ICLR 2021 - [c17]Keyu Tian, Chen Lin, Ser-Nam Lim, Wanli Ouyang, Puneet K. Dokania, Philip H. S. Torr:
A Continuous Mapping For Augmentation Design. NeurIPS 2021: 13732-13743 - [i28]Shyamgopal Karthik, Ameya Prabhu, Puneet K. Dokania, Vineet Gandhi:
No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks. CoRR abs/2104.00795 (2021) - [i27]Francisco Eiras, Motasem Alfarra, M. Pawan Kumar, Philip H. S. Torr, Puneet K. Dokania, Bernard Ghanem, Adel Bibi:
ANCER: Anisotropic Certification via Sample-wise Volume Maximization. CoRR abs/2107.04570 (2021) - [i26]Botos Csaba, Xiaojuan Qi, Arslan Chaudhry, Puneet K. Dokania, Philip H. S. Torr:
Multilevel Knowledge Transfer for Cross-Domain Object Detection. CoRR abs/2108.00977 (2021) - [i25]Jonathan Sadeghi, Blaine Rogers, James Gunn, Thomas Saunders, Sina Samangooei, Puneet Kumar Dokania, John Redford:
A Step Towards Efficient Evaluation of Complex Perception Tasks in Simulation. CoRR abs/2110.02739 (2021) - 2020
- [c16]Ameya Prabhu, Philip H. S. Torr, Puneet K. Dokania:
GDumb: A Simple Approach that Questions Our Progress in Continual Learning. ECCV (2) 2020: 524-540 - [c15]Amartya Sanyal, Philip H. S. Torr, Puneet K. Dokania:
Stable Rank Normalization for Improved Generalization in Neural Networks and GANs. ICLR 2020 - [c14]Arslan Chaudhry, Naeemullah Khan, Puneet K. Dokania, Philip H. S. Torr:
Continual Learning in Low-rank Orthogonal Subspaces. NeurIPS 2020 - [c13]Jishnu Mukhoti, Viveka Kulharia, Amartya Sanyal, Stuart Golodetz, Philip H. S. Torr, Puneet K. Dokania:
Calibrating Deep Neural Networks using Focal Loss. NeurIPS 2020 - [i24]Arslan Chaudhry, Albert Gordo, Puneet K. Dokania, Philip H. S. Torr, David Lopez-Paz:
Using Hindsight to Anchor Past Knowledge in Continual Learning. CoRR abs/2002.08165 (2020) - [i23]Jishnu Mukhoti, Viveka Kulharia, Amartya Sanyal, Stuart Golodetz, Philip H. S. Torr, Puneet K. Dokania:
Calibrating Deep Neural Networks using Focal Loss. CoRR abs/2002.09437 (2020) - [i22]Daniela Massiceti, Viveka Kulharia, Puneet K. Dokania, N. Siddharth, Philip H. S. Torr:
A Revised Generative Evaluation of Visual Dialogue. CoRR abs/2004.09272 (2020) - [i21]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:
Simulation-Based Inference for Global Health Decisions. CoRR abs/2005.07062 (2020) - [i20]Pau de Jorge, Amartya Sanyal, Harkirat S. Behl, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania:
Progressive Skeletonization: Trimming more fat from a network at initialization. CoRR abs/2006.09081 (2020) - [i19]Amartya Sanyal, Puneet K. Dokania, Varun Kanade, Philip H. S. Torr:
How benign is benign overfitting? CoRR abs/2007.04028 (2020) - [i18]Thomas Tanay, Aivar Sootla, Matteo Maggioni, Puneet K. Dokania, Philip H. S. Torr, Ales Leonardis, Gregory G. Slabaugh:
Diagnosing and Preventing Instabilities in Recurrent Video Processing. CoRR abs/2010.05099 (2020) - [i17]Arslan Chaudhry, Naeemullah Khan, Puneet K. Dokania, Philip H. S. Torr:
Continual Learning in Low-rank Orthogonal Subspaces. CoRR abs/2010.11635 (2020) - [i16]Jishnu Mukhoti, Puneet K. Dokania, Philip H. S. Torr, Yarin Gal:
On Batch Normalisation for Approximate Bayesian Inference. CoRR abs/2012.13220 (2020)
2010 – 2019
- 2019
- [j2]Enzo Ferrante, Puneet Kumar Dokania, Rafael Marini, Nikos Paragios:
Weakly Supervised Learning of Metric Aggregations for Deformable Image Registration. IEEE J. Biomed. Health Informatics 23(4): 1374-1384 (2019) - [c12]Arnab Ghosh, Richard Zhang, Puneet K. Dokania, Oliver Wang, Alexei A. Efros, Philip H. S. Torr, Eli Shechtman:
Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation. ICCV 2019: 1171-1180 - [c11]Thalaiyasingam Ajanthan, Puneet K. Dokania, Richard Hartley, Philip H. S. Torr:
Proximal Mean-Field for Neural Network Quantization. ICCV 2019: 4870-4879 - [i15]Arslan Chaudhry, Marcus Rohrbach, Mohamed Elhoseiny, Thalaiyasingam Ajanthan, Puneet Kumar Dokania, Philip H. S. Torr, Marc'Aurelio Ranzato:
Continual Learning with Tiny Episodic Memories. CoRR abs/1902.10486 (2019) - [i14]Amartya Sanyal, Philip H. S. Torr, Puneet K. Dokania:
Stable Rank Normalization for Improved Generalization in Neural Networks and GANs. CoRR abs/1906.04659 (2019) - [i13]Arnab Ghosh, Richard Zhang, Puneet K. Dokania, Oliver Wang, Alexei A. Efros, Philip H. S. Torr, Eli Shechtman:
Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation. CoRR abs/1909.11081 (2019) - [i12]Thalaiyasingam Ajanthan, Kartik Gupta, Philip H. S. Torr, Richard Hartley, Puneet K. Dokania:
Mirror Descent View for Neural Network Quantization. CoRR abs/1910.08237 (2019) - 2018
- [c10]Daniela Massiceti, N. Siddharth, Puneet Kumar Dokania, Philip H. S. Torr:
FlipDial: A Generative Model for Two-Way Visual Dialogue. CVPR 2018: 6097-6105 - [c9]Arnab Ghosh, Viveka Kulharia, Vinay P. Namboodiri, Philip H. S. Torr, Puneet Kumar Dokania:
Multi-Agent Diverse Generative Adversarial Networks. CVPR 2018: 8513-8521 - [c8]Arslan Chaudhry, Puneet Kumar Dokania, Thalaiyasingam Ajanthan, Philip H. S. Torr:
Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence. ECCV (11) 2018: 556-572 - [i11]Arslan Chaudhry, Puneet Kumar Dokania, Thalaiyasingam Ajanthan, Philip H. S. Torr:
Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence. CoRR abs/1801.10112 (2018) - [i10]Daniela Massiceti, N. Siddharth, Puneet Kumar Dokania, Philip H. S. Torr:
FlipDial: A Generative Model for Two-Way Visual Dialogue. CoRR abs/1802.03803 (2018) - [i9]Enzo Ferrante, Puneet Kumar Dokania, Rafael Marini, Nikos Paragios:
Weakly-Supervised Learning of Metric Aggregations for Deformable Image Registration. CoRR abs/1809.09004 (2018) - [i8]Thalaiyasingam Ajanthan, Puneet Kumar Dokania, Richard I. Hartley, Philip H. S. Torr:
Proximal Mean-field for Neural Network Quantization. CoRR abs/1812.04353 (2018) - [i7]Daniela Massiceti, Puneet K. Dokania, N. Siddharth, Philip H. S. Torr:
Visual Dialogue without Vision or Dialogue. CoRR abs/1812.06417 (2018) - 2017
- [c7]Arslan Chaudhry, Puneet Kumar Dokania, Philip H. S. Torr:
Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation. BMVC 2017 - [c6]Qibin Hou, Daniela Massiceti, Puneet Kumar Dokania, Yunchao Wei, Ming-Ming Cheng, Philip H. S. Torr:
Bottom-Up Top-Down Cues for Weakly-Supervised Semantic Segmentation. EMMCVPR 2017: 263-277 - [c5]Enzo Ferrante, Puneet Kumar Dokania, Rafael Marini, Nikos Paragios:
Deformable Registration Through Learning of Context-Specific Metric Aggregation. MLMI@MICCAI 2017: 256-265 - [i6]Arnab Ghosh, Viveka Kulharia, Vinay P. Namboodiri, Philip H. S. Torr, Puneet Kumar Dokania:
Multi-Agent Diverse Generative Adversarial Networks. CoRR abs/1704.02906 (2017) - [i5]Arslan Chaudhry, Puneet Kumar Dokania, Philip H. S. Torr:
Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation. CoRR abs/1707.05821 (2017) - [i4]Enzo Ferrante, Puneet Kumar Dokania, Rafael Marini, Nikos Paragios:
Deformable Registration through Learning of Context-Specific Metric Aggregation. CoRR abs/1707.06263 (2017) - 2016
- [j1]M. Pawan Kumar, Puneet Kumar Dokania:
Rounding-based Moves for Semi-Metric Labeling. J. Mach. Learn. Res. 17: 91:1-91:42 (2016) - [c4]Pritish Mohapatra, Puneet Kumar Dokania, C. V. Jawahar, M. Pawan Kumar:
Partial Linearization Based Optimization for Multi-class SVM. ECCV (5) 2016: 842-857 - [c3]Anton Osokin, Jean-Baptiste Alayrac, Isabella Lukasewitz, Puneet Kumar Dokania, Simon Lacoste-Julien:
Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs. ICML 2016: 593-602 - [i3]Anton Osokin, Jean-Baptiste Alayrac, Isabella Lukasewitz, Puneet Kumar Dokania, Simon Lacoste-Julien:
Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs. CoRR abs/1605.09346 (2016) - [i2]Qinbin Hou, Puneet Kumar Dokania, Daniela Massiceti, Yunchao Wei, Ming-Ming Cheng, Philip H. S. Torr:
Mining Pixels: Weakly Supervised Semantic Segmentation Using Image Labels. CoRR abs/1612.02101 (2016) - 2015
- [c2]Puneet Kumar Dokania, M. Pawan Kumar:
Parsimonious Labeling. ICCV 2015: 1760-1768 - [i1]Puneet Kumar Dokania, M. Pawan Kumar:
Parsimonious Labeling. CoRR abs/1507.01208 (2015) - 2014
- [c1]Puneet Kumar Dokania, Aseem Behl, C. V. Jawahar, M. Pawan Kumar:
Learning to Rank Using High-Order Information. ECCV (4) 2014: 609-623
Coauthor Index
Philip Torr 0001
aka: Philip H. S. Torr
aka: Philip H. S. Torr
[j6] [i46] [i45] [i43] [j5] [j4] [c30] [c29] [c27] [c26] [i42] [i41] [i40] [i38] [i36] [j3] [c25] [c24] [c23] [i35] [i34] [i33] [i32] [i31] [i29] [c22] [c21] [c20] [c18] [c17] [i27] [i26] [c16] [c15] [c14] [c13] [i24] [i23] [i22] [i21] [i20] [i19] [i18] [i17] [i16] [c12] [c11] [i15] [i14] [i13] [i12] [c10] [c9] [c8] [i11] [i10] [i8] [i7] [c7] [c6] [i6] [i5] [i2]
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-10-07 21:24 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
