Our research
2026
Published papers
Foundation Models for Trajectory Planning in Autonomous Driving: A Review of Progress and Open Challenges
Kemal Oksuz, Alexandru Buburuzan, Anthony Knittel, Yuhan Yao, Puneet K. Dokania
Transactions on Machine Learning Research (TMLR) 2026
2024
Published papers
MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection
Kemal Oksuz, Selim Kuzucu, Tom Joy, Puneet K. Dokania
Transactions on Machine Learning Research (TMLR) 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
NeurIPS 2024 (main conference), and ICML 2024 (Mechanistic Interpretability Workshop)
On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines
Selim Kuzucu*, Kemal Oksuz*, Jonathan Sadeghi, Puneet K. Dokania
European Conference on Computer Vision (ECCV) 2024 (Oral Presentation)
Bucketed Ranking-based Losses for Efficient Training of Object Detectors
Feyza Yavuz, Baris Can Cam, Adnan Harun Dogan, Kemal Oksuz, Emre Akbas, Sinan Kalkan
European Conference on Computer Vision (ECCV) 2024
Segment, Select, Correct: A Framework for Weakly-supervised Referring Segmentation
Francisco Eiras, Kemal Oksuz, Adel Bibi, Philip H.S. Torr, Puneet K. Dokania
ECCV 2024 (Instance-Level Recognition Workshop)
Lift-Attend-Splat: Bird’s-eye-view camera-lidar fusion using transformers
James Gunn*, Zygmunt Lenyk*, Anuj Sharma, Andrea Donati, Alexandru Buburuzan, John Redford, Romain Mueller
CVPR 2024 (Workshop on Autonomous Driving)
Fine-tuning can cripple your foundation model; preserving features may be the solution
Jishnu Mukhoti, Yarin Gal, Philip H.S. Torr, Puneet K. Dokania
Transactions on Machine Learning Research (TMLR) 2024 (Featured Certification)
Preprints
Attacking Motion Planners Using Adversarial Perception Errors
Jonathan Sadeghi, Nicholas A. Lord, John Redford, Romain Mueller
Pre-print (2024)
2023
Published papers
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
ICML 2023
Catastrophic overfitting can be induced with discriminative non-robust features
Guillermo Ortiz-Jimenez, Pau de Jorge, Amartya Sanyal, Adel Bibi, Puneet K. Dokania, Pascal Frossard, Grégory Rogez, Philip H.S. Torr
Transactions on Machine Learning Research 2023
Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration
Kemal Oksuz, Tom Joy, Puneet K. Dokania
Conference on Computer Vision and Pattern Recognition (CVPR), June 2023
DiPA: Probabilistic Multi-Modal Interactive Prediction for Autonomous Driving
Anthony Knittel, Majd Hawasly, Stefano V. Albrecht, John Redford, Subramanian Ramamoorthy
IEEE Robotics and Automation Letters, 2023
Planning with Occluded Traffic Agents using Bi-Level Variational Occlusion Models
Filippos Christianos, Peter Karkus, Boris Ivanovic, Stefano V. Albrecht, Marco Pavone
IEEE International Conference on Robotics and Automation (ICRA), 2023
Causal Explanations for Stochastic Sequential Multi-Agent Decision-Making
Balint Gyevnar, Cheng Wang, Christopher G. Lucas, Shay B. Cohen, Stefano V. Albrecht
AAMAS Workshop on Explainable and Transparent AI and Multi-Agent Systems, 2023
Verifiable Goal Recognition for Autonomous Driving with Occlusions
Cillian Brewitt, Massimiliano Tamborski, Cheng Wang, Stefano V. Albrecht
IEEE/RSJ International Conference on Intelligent Robots and Systems, 2023
Sample-dependent Adaptive Temperature Scaling for Improved Calibration
Tom Joy, Francesco Pinto, Ser-Nam Lim, Philip H. S. Torr, and Puneet K. Dokania
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
AAAI Conference on Artificial Intelligence, 2023
Preprints
Comparison of Pedestrian Prediction Models from Trajectory and Appearance Data for Autonomous Driving
Anthony Knittel, Morris Antonello, John Redford and Subramanian Ramamoorthy
ICRA 2023
2022
Published papers
Verifiable Goal Recognition for Autonomous Driving with Occlusions
Cillian Brewitt, Massimiliano Tamborski, Stefano V. Albrecht
NeurIPS Workshop on Machine Learning for Autonomous Driving (ML4AD), 2022
Parameter-free Online Test-time Adaptation
Malik Boudiaf, Romain Mueller, Ismail Ben Ayed, Luca Bertinetto
Conference on Computer Vision and Pattern Recognition (CVPR), June 2022
Self-supervised Test-time Adaptation on Video Data
Fatemeh Azimi, Sebastian Palacio, Federico Raue, Jörn Hees, Luca Bertinetto, Andreas Dengel
Workshop On Applications of Computer Vision (WACV) 2022
An Active Learning Reliability Method for Systems with Partially Defined Performance Functions
Jonathan Sadeghi, Romain Mueller, John Redford
NeurIPS 2022 Workshop on Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems (GPSMDMS) 2022
Attacking deep networks with surrogate-based adversarial black-box methods is easy
Nicholas A. Lord, Romain Mueller, Luca Bertinetto
International Conference on Learning Representations (ICLR) 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
NeurIPS, Conference on Neural Information Processing Systems, 2022, New Orleans, USA
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training
Pau de Jorge, Adel Bibi, Riccardo Volpi, Amartya Sanyal, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania
NeurIPS, Conference on Neural Information Processing Systems, 2022, New Orleans, USA
ANCER: Anisotropic Certification via Sample-wise Volume Maximization
Francisco Eiras, Motasem Alfarra, M. Pawan Kumar, Philip H. S. Torr, Puneet K. Dokania, Bernard Ghanem, Adel Bibi
Transactions on Machine Learning Research, August 2022
Perspectives on the System-level Design of a Safe Autonomous Driving Stack
Majd Hawasly, Jonathan Sadeghi, Morris Antonello, Stefano V. Albrecht, John Redford, Subramanian Ramamoorthy
AI Communications special issue on Multi-agent Systems Research in the UK
An Impartial Take to the CNN vs Transformer Robustness Contest
Francesco Pinto, Philip H. S. Torr, and Puneet K. Dokania
The European Conference on Computer Vision (ECCV) 2022, Tel Aviv
Sample-dependent Adaptive Temperature Scaling for Improved Calibration
Tom Joy, Francesco Pinto, Ser-Nam Lim, Philip H. S. Torr, and Puneet K. Dokania
ICML, Distribution-Free Uncertainty Quantification Workshop 2022, Baltimore, USA
Catastrophic overfitting is a bug but also a feature
Guillermo Ortiz-Jiménez, Pau de Jorge, Amartya Sanyal, Adel Bibi, Puneet K. Dokania, Pascal Frossard, Gregory Rogéz, Philip H.S. Torr
ICML, New Frontiers in Adversarial Machine Learning (AdvML) 2022, Baltimore, USA
Flash: Fast and Light Motion Prediction for Autonomous Driving with Bayesian Inverse Planning and Learned Motion Profiles
Morris Antonello, Mihai Dobre, Stefano V. Albrecht, John Redford, Subramanian Ramamoorthy
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022
A Human-Centric Method for Generating Causal Explanations in Natural Language for Autonomous Vehicle Motion Planning
Balint Gyevnar, Massimiliano Tamborski, Cheng Wang, Christopher G. Lucas, Shay B. Cohen, Stefano V. Albrecht
IJCAI Workshop on Artificial Intelligence for Autonomous Driving (AI4AD), 2022
Preprints
DiPA: Probabilistic Multi-Modal Interactive Prediction for Autonomous Driving
Anthony Knittel, Majd Hawasly, Stefano V. Albrecht, John Redford, Subramanian Ramamoorthy
arXiv preprint arXiv:2210.06106, October 2022
Beyond RMSE: Do machine-learned models of road user interaction produce human-like behavior?
Aravinda Ramakrishnan Srinivasan, Yi-Shin Lin, Morris Antonello, Anthony Knittel, Mohamed Hasan, Majd Hawasly, John Redford, Subramanian Ramamoorthy, Matteo Leonetti, Jac Billington, Richard Romano, Gustav Markkula
arXiv preprint arXiv:2206.11110, August 2022
2021
Published papers
Are Vision Transformers Always More Robust Than Convolutional Neural Networks?
Francesco Pinto, Philip Torr, Puneet K Dokania
NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications
Mix-MaxEnt: Improving Accuracy and Uncertainty Estimates of Deterministic Neural Networks
Francesco Pinto, Harry Yang, Ser-Nam Lim, Philip Torr, Puneet K Dokania
NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications
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
NeurIPS 2021 Workshop on Machine Learning for Autonomous Driving
On Episodes, Prototypical Networks, and Few-shot Learning
Steinar Laenen, Luca Bertinetto
To appear at the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021)
Do Different Tracking Tasks Require Different Appearance Models?
Zhongdao Wang, Hengshuang Zhao, Ya-Li Li, Shengjin Wang, Philip H.S. Torr, Luca Bertinetto
To appear at the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021)
A Continuous Mapping For Augmentation Design
Keyu Tian, Chen Lin, Ser-Nam Lim, Wanli Ouyang, Puneet K. Dokania, Philip Torr
To appear at the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021)
Smart Pointers and Shared Memory Synchronisation for Efficient Inter-process Communication in ROS on an Autonomous Vehicle
Costin Iordache, Stephen M. Fendyke, Mike J. Jones, Robert A. Buckley
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Interpretable Goal Recognition in the Presence of Occluded Factors for Autonomous Vehicles
Josiah P. Hanna, Arrasy Rahman, Elliot Fosong, Francisco Eiras, Mihai Dobre, John Redford, Subramanian Ramamoorthy, Stefano V. Albrecht
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
GRIT: Fast, Interpretable, and Verifiable Goal Recognition with Learned Decision Trees for Autonomous Driving
Cillian Brewitt, Balint Gyevnar, Samuel Garcin, Stefano V. Albrecht
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
PILOT: Efficient Planning by Imitation Learning and Optimisation for Safe Autonomous Driving
Henry Pulver, Francisco Eiras, Ludovico Carozza, Majd Hawasly, Stefano V. Albrecht and Subramanian Ramamoorthy
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Interpretable Goal-based Prediction and Planning for Autonomous Driving
Stefano V. Albrecht, Cillian Brewitt, John Wilhelm, Balint Gyevnar, Francisco Eiras, Mihai Dobre, Subramanian Ramamoorthy
IEEE International Conference on Robotics and Automation (ICRA), 2021, Xi'an China
Recurrently Estimating Reflective Symmetry Planes from Partial Pointclouds
Mihaela Cătălina Stoian, Tommaso Cavallari
CVPR 2021 Workshop on 3D Vision and Robotics
A Two-Stage Optimization-based Motion Planner for Safe Urban Driving
Francisco Eiras, Majd Hawasly, Stefano V. Albrecht, Subramanian Ramamoorthy
IEEE Transactions on Robotics (T-RO), 2021
Resolving Conflict in Decision-Making for Autonomous Driving
Jack Geary, Subramanian Ramamoorthy, Henry Gouk
Robotics: Science and Systems (R:SS), 2021
Progressive Skeletonization: Trimming more fat from a network at initialization
Pau de Jorge, Amartya Sanyal, Harkirat S. Behl, Gregory Rogez, Philip H. S. Torr, Puneet K. Dokania
International Conference on Learning Representations (ICLR) 2021
No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks
Shyamgopal Karthik, Ameya Prabhu, Puneet K. Dokania, Vineet Gandhi
International Conference on Learning Representations (ICLR) 2021
How benign is benign overfitting?
Amartya Sanyal, Puneet K Dokania, Varun Kanade, Philip H.S. Torr
International Conference on Learning Representations (ICLR) 2021
Scalable FPGA Median Filtering via a Directional Median Cascade
Oscar Rahnama, Stuart Golodetz, Tommaso Cavallari, Philip H.S. Torr
2021 IEEE 29th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM) (poster, non-archival)
2020
Published papers
Lower dimensional kernels for video discriminators
E. Kahembwe, S. Ramamoorthy
Neural Networks Journal, Special Issue on Deep Neural Network Representation and Generative Adversarial Learning, 2020
Continual Learning in Low-rank Orthogonal Subspaces
Arslan Chaudhry, Naeemullah Khan, Puneet K. Dokania, Philip H.S. Torr
Advances in Neural Information Processing Systems (NeurIPS), December 2020
GDumb: A Simple Approach that Questions Our Progress in Continual Learning
Ameya Prabhi, Philip H.S. Torr, Puneet K. Dokania
European Conference on Computer Vision (ECCV) (oral), August 2020
PaRoT: A Practical Framework for Robust Deep Neural Network Training
Edward Ayers, Francisco Eiras, Majd Hawasly, Iain Whiteside
NASA Formal Methods. NFM 2020. Lecture Notes in Computer Science, vol 12229, August 2020
Beyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor Scenes
Johanna Wald, Torsten Sattler, Stuart Golodetz, Tommaso Cavallari and Federico Tombari
European Conference on Computer Vision (ECCV), August 2020
Calibrating Deep Neural Networks using Focal Loss
Jishnu Mukhoti, Viveka Kulharia, Amartya Sanyal, Stuart Golodetz, Philip H S Torr and Puneet K Dokania
Advances in Neural Information Processing Systems (NeurIPS), December 2020
An Optimization-based Motion Planner for Safe Autonomous Driving
Francisco Eiras, Majd Hawasly, Stefano V. Albrecht, Subramanian Ramamoorthy
RSS 2020 Workshop in Robust Autonomy
Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks
Luca Bertinetto*, Romain Mueller*, Konstantinos Tertikas, Sina Samangooei and Nicholas A Lord*
Conference on Computer Vision and Pattern Recognition (CVPR), June 2020
Simplifying TugGraph using Zipping Algorithms
Stuart Golodetz, Anurag Arnab, Irina Voiculescu and Stephen Cameron
Pattern Recognition, July 2020
FPR – Fast Path Risk Algorithm to Evaluate Collision Probability
Andrew Blake, Alejandro Bordallo, Kamen Brestnichki, Majd Hawasly, Svetlin Valentinov Penkov, Subramanian Ramamoorthy, Alexandre Silva
IEEE Robotics and Automation Letters ( Volume: 5, Issue: 1, Jan 2020)
Scalable FPGA Median Filtering using Multiple Efficient Passes
Oscar Rahnama, Tommaso Cavallari, Philip H. S. Torr, Stuart Golodetz
Proceedings of the 2020 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (PFGA’20) (February 2021 Pages 313-313) (poster, non-archival)
2019
Published papers
Anchor Diffusion for Unsupervised Video Object Segmentation
Zhao Yang*, Qiang Wang*, Luca Bertinetto, Weiming Hu, Song Bai and Philip H.S. Torr
International Conference on Computer Vision (ICCV), October 2019
Correct-by-Construction Advanced Driver Assistance Systems based on a Cognitive Architecture
Francisco Eiras, Morteza Lahijanian, and Marta Kwiatkowska
Proc. IEEE Connected and Automated Vehicles Symposium (IEEE CAVS), 2019
Meta-learning with differentiable closed-form solvers
Luca Bertinetto, João Henriques, Philip H.S. Torr and Andrea Vedaldi
International Conference on Learning Representations (ICLR), May 2019
Fast Online Object Tracking and Segmentation: A Unifying Approach
Qiang Wang*, Li Zhang*, Luca Bertinetto*, Weiming Hu and Philip H.S. Torr
Conference on Computer Vision and Pattern Recognition (CVPR), June 2019
From explanation to synthesis: Compositional program induction for learning from demonstration
Michael Burke, Svetlin Penkov and Subramanian Ramamoorthy
In Proc. Robotics: Science and Systems(R:SS), 2019
Iterative model-based Reinforcement Learning using simulations in the Differentiable Neural Computer
Adeel Mufti, Svetlin Penkovand Subramanian Ramamoorthy
In Proc. ICML Workshop on Multi-Task and Lifelong Reinforcement Learning, 2019
Learning programmatically structured representations with preceptor gradients
Svetlin Penkov and Subramanian Ramamoorthy
In Proc. International Conference on Learning Representations (ICLR), 2019
Learning to Adapt for Stereo
Alessio Tonioni, Oscar Rahnama, Tom Joy, Ajanthan Thalaiyasingam, Luigi Di Stefano and Philip H.S. Torr
Conference on Computer Vision and Pattern Recognition (CVPR), June 2019
Let's Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera Relocalisation
Tommaso Cavallari*, Luca Bertinetto, Jishnu Mukhoti, Philip H.S. Torr and Stuart Golodetz*
International Conference on 3D Vision (3DV), September 2019
Real-Time RGB-D Camera Pose Estimation in Novel Scenes using a Relocalisation Cascade
Tommaso Cavallari*, Stuart Golodetz*, Nicholas A Lord*, Julien Valentin*, Victor A Prisacariu, Luigi Di Stefano and Philip H.S. Torr
Transactions on Pattern Analysis and Machine Intelligence (TPAMI): Special Issue on RGB-D Vision, 2019
Real-Time Highly Accurate Dense Depth on a Power Budget using an FPGA-CPU Hybrid SoC
Oscar Rahnama, Tommaso Cavallari, Stuart Golodetz, Alessio Tonioni, Tom Joy, Luigi Di Stefano, Simon Walker and Philip H.S. Torr
IEEE Transactions on Circuits and Systems II (TCAS-II): Express Briefs, 2019
Towards Provably Correct Driver Assistance Systems through Stochastic Cognitive Modeling
Francisco Eiras and Morteza Lahijanian
Workshop on Safe Autonomy, Robotics: Science and Systems, 2019
Preprints
Straight to Shapes++: Real-time Instance Segmentation Made More Accurate
Laurynas Miksys*, Saumya Jetley*, Michael Sapienza, Stuart Golodetz and Philip H.S. Torr
arXiv preprint arXiv:1905.11358, May 2019
Certification of Highly Automated Vehicles for Use on UK Roads
P. Koopman, R. Hierons, S. Khastgir, J.A. Clark, M. Fisher, R. Alexander, K. Eder, P. Thomas, G. Barrett, Philip H.S. Torr, A. Blake, S. Ramamoorthy, J. McDermid
2018
Published papers
Collaborative Large-Scale Dense 3D Reconstruction with Online Inter-Agent Pose Optimisation
Stuart Golodetz*, Tommaso Cavallari*, Nicholas A Lord*, Victor A Prisacariu, David W Murray and Philip H.S. Torr
IEEE Transactions on Visualization and Computer Graphics 24(11), 2018
A Dataset for Lane Instance Segmentation in Urban Environments
Brook Roberts, Sebastian Kaltwang, Sina Samangooei, Mark Pender-Bare, Konstantinos Tertikas, and John Redford
European Conference on Computer Vision (ECCV), pages 533-549, September 2018
Long-term Tracking in the Wild: A Benchmark
Jack Valmadre*, Luca Bertinetto*, João F. Henriques, Ran Tao, Andrea Vedaldi, Arnold Smeulders, Philip H.S. Torr, and Efstratios Gavves*
European Conference on Computer Vision (ECCV), pages 670-685, September 2018
R3SGM: Real-time Raster-Respecting Semi-Global Matching for Power-Constrained Systems
Oscar Rahnama, Tommaso Cavallari*, Stuart Golodetz*, Simon Walker, and Philip H.S. Torr
International Conference on Field-Programmable Technology (FPT), December 2018
Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
Arslan Chaudry*, Puneet K Dokania*, Ajanthan Thalaiyasingam* and Philip H.S. Torr
European Conference on Computer Vision (ECCV), pages 532-547, September 2018
Topological Signatures For Fast Mobility Analysis
Abhirup Ghosh, Benedek Rozemberczki, Subramanian Ramamoorthy, and Rik Sarkar
International Conference on Advances in Geographic Information Systems (SIGSPATIAL), pages 159-168, November 2018
With Friends Like These, Who Needs Adversaries?
Saumya Jetley*, Nicholas A. Lord*, and Philip H.S. Torr
Advances in Neural Information Processing Systems (NeurIPS), pages 10772-10782, December 2018
2017
Published papers
Multi-Scale Activity Estimation with Spatial Abstractions
Majd Hawasly, Florian T. Pokorny, and Subramanian Ramamoorthy
International Conference on Geometric Science of Information (GSI), pages 273-281, November 2017
Privacy Notice
Five AI Limited, Fora, 20 Station Road, Cambridge, CB1 2JD.
Registered under company number 10423075 in England & Wales.
© Five AI Limited 2024