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

by   Daniela Massiceti, et al.

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://bit.ly/2OyElCj and the code to run the benchmark at https://bit.ly/39YgiUW.


page 1

page 4

page 14

page 17

page 18

page 19

page 20

page 27


FewSOL: A Dataset for Few-Shot Object Learning in Robotic Environments

We introduce the Few-Shot Object Learning (FewSOL) dataset for object re...

CURE-OR: Challenging Unreal and Real Environments for Object Recognition

In this paper, we introduce a large-scale, controlled, and multi-platfor...

F-SIOL-310: A Robotic Dataset and Benchmark for Few-Shot Incremental Object Learning

Deep learning has achieved remarkable success in object recognition task...

CORe50: a New Dataset and Benchmark for Continuous Object Recognition

Continuous/Lifelong learning of high-dimensional data streams is a chall...

On zero-shot recognition of generic objects

Many recent advances in computer vision are the result of a healthy comp...

Delta-encoder: an effective sample synthesis method for few-shot object recognition

Learning to classify new categories based on just one or a few examples ...

Objaverse: A Universe of Annotated 3D Objects

Massive data corpora like WebText, Wikipedia, Conceptual Captions, WebIm...

Please sign up or login with your details

Forgot password? Click here to reset