10 citations · 10 across the 3 of their papers we have counts for
3 papers
QueryAdapter: Rapid Adaptation of Vision-Language Models in Response to Natural Language Queries
Nicolas Harvey Chapman, Feras Dayoub, Will Browne +1
A domain shift exists between the large-scale, internet data used to train a Vision-Language Model (VLM) and the raw image streams collected by a robot. Existing adaptation strateg…
Enhancing Embodied Object Detection through Language-Image Pre-training and Implicit Object Memory
Nicolas Harvey Chapman, Feras Dayoub, Will Browne +1
Deep-learning and large scale language-image training have produced image object detectors that generalise well to diverse environments and semantic classes. However, single-image…
Predicting Class Distribution Shift for Reliable Domain Adaptive Object Detection
Nicolas Harvey Chapman, Feras Dayoub, Will Browne +1
Unsupervised Domain Adaptive Object Detection (UDA-OD) uses unlabelled data to improve the reliability of robotic vision systems in open-world environments. Previous approaches to…