no code implementations • 22 Dec 2023 • James Gunn, Zygmunt Lenyk, Anuj Sharma, Andrea Donati, Alexandru Buburuzan, John Redford, Romain Mueller
Combining complementary sensor modalities is crucial to providing robust perception for safety-critical robotics applications such as autonomous driving (AD).
no code implementations • 21 Nov 2023 • Jonathan Sadeghi, Nicholas A. Lord, John Redford, Romain Mueller
Autonomous driving (AD) systems are often built and tested in a modular fashion, where the performance of different modules is measured using task-specific metrics.
1 code implementation • 5 Oct 2022 • Jonathan Sadeghi, Romain Mueller, John Redford
This enables active learning Gaussian process methods to be applied to problems where the performance of the system is sometimes undefined, and we demonstrate the effectiveness of our approach by testing our methodology on synthetic numerical examples for the autonomous driving domain.
1 code implementation • 23 Sep 2022 • Edward Ayers, Jonathan Sadeghi, John Redford, Romain Mueller, Puneet K. Dokania
There is a longstanding interest in capturing the error behaviour of object detectors by finding images where their performance is likely to be unsatisfactory.
1 code implementation • ICLR 2022 • Nicholas A. Lord, Romain Mueller, Luca Bertinetto
A recent line of work on black-box adversarial attacks has revived the use of transfer from surrogate models by integrating it into query-based search.
1 code implementation • CVPR 2022 • Malik Boudiaf, Romain Mueller, Ismail Ben Ayed, Luca Bertinetto
An interesting and practical paradigm is online test-time adaptation, according to which training data is inaccessible, no labelled data from the test distribution is available, and adaptation can only happen at test time and on a handful of samples.
1 code implementation • CVPR 2020 • Luca Bertinetto, Romain Mueller, Konstantinos Tertikas, Sina Samangooei, Nicholas A. Lord
Deep neural networks have improved image classification dramatically over the past decade, but have done so by focusing on performance measures that treat all classes other than the ground truth as equally wrong.