ORBIT: A real-world few-shot dataset for teachable object recognition collected from people who are blind or low vision

Object recognition 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, grounded in a real-world application of teachable object recognizers for people who are blind/low vision. We provide a full, unfiltered dataset of 4,733 videos of 588 objects recorded by 97 people who are blind/low-vision on their mobile phones, and a benchmark dataset of 3,822 videos of 486 objects collected by 77 collectors.
The code for loading the dataset, computing all benchmark metrics, and running the baseline models is available at https://github.com/microsoft/ORBIT-Dataset
This version comprises several zip files:- train, validation, test: benchmark dataset, organised by collector, with raw videos split into static individual frames in jpg format at 30FPS- other: data not in the benchmark set, organised by collector, with raw videos split into static individual frames in jpg format at 30FPS (please note that the train, validation, test, and other files make up the unfiltered dataset)- *_224: as for the benchmark, but static individual frames are scaled down to 224 pixels.- *_unfiltered_videos: full unfiltered dataset, organised by collector, in mp4 format.

目标识别（Object recognition）目前仍主要依赖每个物体类别下的大量高质量训练样本。与之相对，仅通过少量样本学习新物体的能力，可催生从机器人技术到用户个性化定制等诸多极具影响力的应用场景。然而，当前绝大多数少样本学习（few-shot learning）研究的基准数据集，均未能涵盖实际部署时真实应用会面临的高多样性场景。为填补这一研究空白，我们推出了ORBIT数据集，其落地场景为面向视障/低视力人群的可教学目标识别器的真实应用。我们提供了完整的无过滤数据集：由97名视障/低视力使用者通过手机录制的588个物体、总计4733段视频；同时还提供了基准数据集：由77名采集者收集的486个物体、总计3822段视频。
用于加载该数据集、计算所有基准指标以及运行基准模型的代码已开源至：https://github.com/microsoft/ORBIT-Dataset
本数据集版本包含多个压缩包：
- train、validation、test：基准数据集，按采集者维度组织，原始视频已按30FPS帧率拆分为静态单帧jpg格式文件
- other：不属于基准数据集的其余数据，同样按采集者维度组织，原始视频已按30FPS帧率拆分为静态单帧jpg格式文件（请注意：train、validation、test与other文件共同构成完整的无过滤数据集）
- *_224：与基准数据集结构一致，但静态单帧图像已被缩放至224像素尺寸
- *_unfiltered_videos：完整的无过滤数据集，按采集者维度组织，格式为mp4原始视频文件