ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition

TL;DR

The paper introduces ORBIT, a challenging real-world few-shot object recognition dataset and benchmark designed for teachable recognizers, especially aiding visually impaired users, highlighting the need for robustness in practical applications.

Contribution

It provides a large, real-world dataset and benchmark for few-shot object recognition, focusing on high-variation conditions relevant to blind/low-vision users, which was lacking in prior benchmarks.

Findings

Achieved state-of-the-art results on the ORBIT benchmark.

Demonstrated significant room for improvement in robustness.

Highlighted the importance of real-world variation in few-shot learning.

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.