Object recognition systems have made spectacular advances in recent years, but they rely on training datasets with thousands of high-quality, labelled examples per object category. Learning new objects from only a few examples could open the door to many new applications. For example, robotics manufacturing requires a system to quickly learn new parts, while assistive technologies need to be adapted to the unique needs and abilities of every individual.
Few-shot learning aims to reduce these demands by training models that can recognize completely novel objects from only a few examples, say 1 to 10. In particular, meta-learning algorithms—which ‘learn to learn’ using episodic training—are a promising approach to significantly reduce the number of training examples needed to train a model. However, most research in few-shot learning has been driven by benchmark datasets that lack the high variation that applications face when deployed in the real world.
In partnership with City, University of London, we introduce the ORBIT dataset and few-shot benchmark for learning new objects from only a few, high-variation examples to close this gap. The dataset and benchmark set a new standard for evaluating machine learning models in few-shot, high-variation learning scenarios, which will help to train models for higher performance in real-world scenarios. This work is done in collaboration with a multi-disciplinary team, including Simone Stumpf, Lida Theodorou, and Matthew Tobias Harris from City, University of London and Luisa Zintgraf from University of Oxford. The work was funded by Microsoft AI for Accessibility. You can read more about the ORBIT research project and its goal to make AI more inclusive of people with disabilities in this AI Blog post.
You can learn more about the work in our research papers: “ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition,” published at the International Conference of Computer Vision (ICCV 2021), and “Disability-first Dataset Creation: Lessons from Constructing a Dataset for Teachable Object Recognition with Blind and Low Vision Data Collectors,” published at the 23rd International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS 2021).
You’re also invited to join Senior Researcher Daniela Massiceti for a talk about
This article is purposely trimmed, please visit the source to read the full article.