Alert button
Picture for Puneet K. Dokania

Puneet K. Dokania

Alert button

Placing Objects in Context via Inpainting for Out-of-distribution Segmentation

Feb 26, 2024
Pau de Jorge, Riccardo Volpi, Puneet K. Dokania, Philip H. S. Torr, Gregory Rogez

Viaarxiv icon

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

Feb 13, 2024
Ameya Prabhu, Shiven Sinha, Ponnurangam Kumaraguru, Philip H. S. Torr, Ozan Sener, Puneet K. Dokania

Viaarxiv icon

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

Oct 23, 2023
Francisco Eiras, Kemal Oksuz, Adel Bibi, Philip H. S. Torr, Puneet K. Dokania

Viaarxiv icon

MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection

Sep 27, 2023
Kemal Oksuz, Selim Kuzucu, Tom Joy, Puneet K. Dokania

Figure 1 for MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection
Figure 2 for MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection
Figure 3 for MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection
Figure 4 for MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection
Viaarxiv icon

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

Aug 25, 2023
Jishnu Mukhoti, Yarin Gal, Philip H. S. Torr, Puneet K. Dokania

Figure 1 for Fine-tuning can cripple your foundation model; preserving features may be the solution
Figure 2 for Fine-tuning can cripple your foundation model; preserving features may be the solution
Figure 3 for Fine-tuning can cripple your foundation model; preserving features may be the solution
Figure 4 for Fine-tuning can cripple your foundation model; preserving features may be the solution
Viaarxiv icon

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

Jul 03, 2023
Kemal Oksuz, Tom Joy, Puneet K. Dokania

Figure 1 for Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration
Figure 2 for Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration
Figure 3 for Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration
Figure 4 for Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration
Viaarxiv icon

Graph Inductive Biases in Transformers without Message Passing

May 27, 2023
Liheng Ma, Chen Lin, Derek Lim, Adriana Romero-Soriano, Puneet K. Dokania, Mark Coates, Philip Torr, Ser-Nam Lim

Figure 1 for Graph Inductive Biases in Transformers without Message Passing
Figure 2 for Graph Inductive Biases in Transformers without Message Passing
Figure 3 for Graph Inductive Biases in Transformers without Message Passing
Figure 4 for Graph Inductive Biases in Transformers without Message Passing
Viaarxiv icon

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

Sep 24, 2022
Jishnu Mukhoti, Tsung-Yu Lin, Bor-Chun Chen, Ashish Shah, Philip H. S. Torr, Puneet K. Dokania, Ser-Nam Lim

Figure 1 for Raising the Bar on the Evaluation of Out-of-Distribution Detection
Figure 2 for Raising the Bar on the Evaluation of Out-of-Distribution Detection
Figure 3 for Raising the Bar on the Evaluation of Out-of-Distribution Detection
Figure 4 for Raising the Bar on the Evaluation of Out-of-Distribution Detection
Viaarxiv icon

Query-based Hard-Image Retrieval for Object Detection at Test Time

Sep 23, 2022
Edward Ayers, Jonathan Sadeghi, John Redford, Romain Mueller, Puneet K. Dokania

Figure 1 for Query-based Hard-Image Retrieval for Object Detection at Test Time
Figure 2 for Query-based Hard-Image Retrieval for Object Detection at Test Time
Figure 3 for Query-based Hard-Image Retrieval for Object Detection at Test Time
Figure 4 for Query-based Hard-Image Retrieval for Object Detection at Test Time
Viaarxiv icon

An Impartial Take to the CNN vs Transformer Robustness Contest

Jul 22, 2022
Francesco Pinto, Philip H. S. Torr, Puneet K. Dokania

Figure 1 for An Impartial Take to the CNN vs Transformer Robustness Contest
Figure 2 for An Impartial Take to the CNN vs Transformer Robustness Contest
Figure 3 for An Impartial Take to the CNN vs Transformer Robustness Contest
Figure 4 for An Impartial Take to the CNN vs Transformer Robustness Contest
Viaarxiv icon