ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition
ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition
复制标题
DOI：
10.1109/iccv48922.2021.01064
复制
发表时间：
2021-04
期刊：
影响因子：
--
通讯作者：
Daniela Massiceti;L. Zintgraf;J. Bronskill;Lida Theodorou;Matthew Tobias Harris;Edward Cutrell;C. Morrison;Katja Hofmann;Simone Stumpf
中科院分区：
文献类型：
--
作者：
Daniela Massiceti;L. Zintgraf;J. Bronskill;Lida Theodorou;Matthew Tobias Harris;Edward Cutrell;C. Morrison;Katja Hofmann;Simone Stumpf
在过去的十年中，对象识别取得了巨大的进步，但相比之下，每个对象都依靠许多高质量的培训示例 - 但是，学习研究是由基准数据集驱动的，这些数据集缺乏这些应用程序在现实世界中部署时会面临的高度差异缩小此差距，我们介绍了轨道数据集和基准，该数据集和基于盲人/低视觉的人的现实世界应用对象识别器。他们的手机的愿景Benchmark的第一个最先进，并表明有巨大的创新范围，有可能影响广泛的现实世界愿景应用程序，包括盲人/低视觉社区的工具。 ：//doi.org/10.25383/city.14294597和基准代码https://github.com/microsoft/orbit-dataset。
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.