@inproceedings{massiceti2021orbit,
author = {Massiceti, Daniela and Zintgraf, Luisa and Bronskill, John and Theodorou, Lida and Tobias Harris, Matthew and Cutrell, Ed and Morrison, Cecily and Hofmann, Katja and Stumpf, Simone},
title = {ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition},
booktitle = {ICCV 2021},
year = {2021},
month = {October},
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 a 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, and 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 first state-of-the-art on the benchmark and show that 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. The dataset is available at https://doi.org/10.25383/city.14294597 and the code to run the benchmark at https://github.com/microsoft/ORBIT-Dataset.},
url = {http://approjects.co.za/?big=en-us/research/publication/orbit-dataset/},
}