Puneet K. Dokania
University of Oxford
H-index: 24
Europe-United Kingdom
Top articles of Puneet K. Dokania
Title | Journal | Author(s) | Publication Date |
---|---|---|---|
Extracting features from sensor data | 2024/3/14 | ||
Placing Objects in Context via Inpainting for Out-of-distribution Segmentation | arXiv preprint arXiv:2402.16392 | Pau de Jorge Riccardo Volpi Puneet K Dokania Philip HS Torr Gregory Rogez | 2024/2/26 |
RanDumb: A Simple Approach that Questions the Efficacy of Continual Representation Learning | arXiv preprint arXiv:2402.08823 | Ameya Prabhu Shiven Sinha Ponnurangam Kumaraguru Philip HS Torr Ozan Sener | 2024/2/13 |
Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation | arXiv preprint arXiv:2310.13479 | Francisco Eiras Kemal Oksuz Adel Bibi Philip HS Torr Puneet K Dokania | 2023/10/20 |
Computationally Budgeted Continual Learning: What Does Matter? | Ameya Prabhu Hasan Abed Al Kader Hammoud Puneet K Dokania Philip HS Torr Ser-Nam Lim | 2023 | |
MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection | arXiv preprint arXiv:2309.14976 | Kemal Oksuz Selim Kuzucu Tom Joy Puneet K Dokania | 2023/9/26 |
Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration | Kemal Oksuz Tom Joy Puneet K Dokania | 2023 | |
Fine-tuning can cripple your foundation model; preserving features may be the solution | arXiv preprint arXiv:2308.13320 | Jishnu Mukhoti Yarin Gal Philip HS Torr Puneet K Dokania | 2023/8/25 |
Query-based Hard-Image Retrieval for Object Detection at Test Time | Edward Ayers Jonathan Sadeghi John Redford Romain Mueller Puneet K Dokania | 2023 | |
Graph Inductive Biases in Transformers without Message Passing | In ICML 2023 | Liheng Ma Chen Lin Derek Lim Adriana Romero-Soriano Puneet K Dokania | 2023/5/27 |
Raising the bar on the evaluation of out-of-distribution detection | Jishnu Mukhoti Tsung-Yu Lin Bor-Chun Chen Ashish Shah Philip HS Torr | 2023 | |
Online continual learning without the storage constraint | arXiv preprint arXiv:2305.09253 | Ameya Prabhu Zhipeng Cai Puneet Dokania Philip Torr Vladlen Koltun | 2023/5/16 |
Sample-dependent Adaptive Temperature Scaling for Improved Calibration | In AAAI 2023 (Safe and Robust AI Track) | Tom Joy Francesco Pinto Ser-Nam Lim Philip HS Torr Puneet K Dokania | 2023 |
Catastrophic overfitting can be induced with discriminative non-robust features | Transactions on Machine Learning Research | Guillermo Ortiz-Jimenez Pau de Jorge Amartya Sanyal Adel Bibi Puneet K Dokania | 2023/5/12 |
Diagnosing and Preventing Instabilities in Recurrent Video Processing | IEEE Transactions on Pattern Analysis and Machine Intelligence | Thomas Tanay Aivar Sootla Matteo Maggioni Puneet K Dokania Philip Torr | 2022/3/17 |
RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness | Neural Information Processing Systems (NeurIPS) 2022 | Francesco Pinto Harry Yang Ser-Nam Lim Philip HS Torr Puneet K Dokania | 2022/12 |
Catastrophic overfitting is a bug but it is caused by features | Guillermo Ortiz-Jimenez Pau de Jorge Amartya Sanyal Adel Bibi Puneet K Dokania | 2022/9/29 | |
Ancer: Anisotropic certification via sample-wise volume maximization | Transactions on Machine Learning Research | Francisco Eiras Motasem Alfarra M Pawan Kumar Philip HS Torr Puneet K Dokania | 2022 |
An Impartial Take to the CNN vs Transformer Robustness Contest | In The European Conference on Computer Vision (ECCV) 2022 | Francesco Pinto Philip HS Torr Puneet K Dokania | 2022/7/22 |
Catastrophic overfitting is a bug but also a feature | ICML 2022 Workshop on New Frontiers in Adversarial Machine Learning | Guillermo Ortiz-Jiménez Pau de Jorge Amartya Sanyal Adel Bibi Puneet K Dokania | 2022/6/16 |