FiftyOne

At Allstate, my team works on auto vehicle damage inspection. Verifying the damage to a vehicle can take an insurance claim agent hours to verify, but using computer vision and FiftyOne, we can segment the parts of vehicles first, then detect the damages, and finally match the damage to repair costs and generate reports for the adjusters.

We use FiftyOne to organize large research datasets. My favorite feature is the ability to view distributions over image attributes in the dataset, and filter the dataset by those attributes.

At Protex AI we develop a platform to monitor worker health and safety using existing CCTV infrastructure. Our core computer vision technologies are object detection, classification, and pose estimation. We use FiftyOne as a vital component in our pipeline to validate dataset annotations, intelligently subsample datasets to ensure balance, and also to visualize and debug model predictions to assess accuracy.

We’ve been using FiftyOne for over a year and it has drastically changed the way we work. The ability to easily display and analyze our images and their metadata, including experiment results, has been a refreshing change compared to the way we've worked before - mainly writing our own metrics and viewers. I've personally used FiftyOne for a segmentation model I've trained - trying to analyze the results and visually see what my model outputs has been really easy and fluid thanks to FiftyOne.

FiftyOne provides a superior interface for dealing with computer vision data. Its extensive Python package lets you do almost any data transformation, perform similarity search, and easily evaluate model predictions.

FiftyOne is the backbone of our Data Engine. It helps us to clean and relabel our datasets efficiently, and convert our model predictions into large scale training datasets with a little help from CVAT.

Wildlife.ai is developing the Wildlife Watcher, an open source smart camera trap that captures images of a much wider variety of animals than is possible today, while also automatically producing valuable data insights using machine learning. The cameras have already outperformed traditional monitoring tools to record the presence of invasive and native species in New Zealand. To make the Wildlife Watchers available to the wider community, Wildlife.ai is using FiftyOne and other open source software to enable users to easily analyze the camera data and create their own models.