ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition
Abstract
Object recognition has made great advances in the last decade, but predominately still relies on many high-quality training examples per object category. In contrast, learning new objects from only a few examples could enable many impactful applications from robotics to user personalization. Most few-shot learning research, however, has been driven by benchmark datasets that lack the high variation that these applications will face when deployed in the real-world. To close this gap, we present the ORBIT dataset and benchmark, grounded in the real-world application of teachable object recognizers for people who are blind/low-vision. The dataset contains 3,822 videos of 486 objects recorded by people who are blind/low-vision on their mobile phones. The benchmark reflects a realistic, highly challenging recognition problem, providing a rich playground to drive research in robustness to few-shot, high-variation conditions. We set the benchmark's first state-of-the-art and show there is massive scope for further innovation, holding the potential to impact a broad range of real-world vision applications including tools for the blind/low-vision community. We release the dataset at https://doi.org/10.25383/city.14294597 and benchmark code at https://github.com/microsoft/ORBIT-Dataset.
Cite
@article{arxiv.2104.03841,
title = {ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition},
author = {Daniela Massiceti and Luisa Zintgraf and John Bronskill and Lida Theodorou and Matthew Tobias Harris and Edward Cutrell and Cecily Morrison and Katja Hofmann and Simone Stumpf},
journal= {arXiv preprint arXiv:2104.03841},
year = {2021}
}
Comments
IEEE/CVF International Conference on Computer Vision (ICCV), 2021