Facebook’s AI vision tools are now open source. DeepMask, SharpMask, and MultiPathNet will be made available to anyone interested in computer vision. The ultimate goal is to help the Artificial Intelligence community make new advancements in this field.
The three tools are the work of Facebook’s Artificial Intelligence Research (FAIR) team. They were created to teach computers how to intelligently classify images and recognize the objects, people, and locations in them.
“We’re making the code for DeepMask+SharpMask as well as MultiPathNet — along with our research papers and demos related to them — open and accessible to all, with the hope that they’ll help rapidly advance the field of machine vision. As we continue improving these core technologies we’ll continue publishing our latest results and updating the open source tools we make available to the community,” announced the FAIR team on their blog.
Why is visual recognition important? There are many potential uses for this type of technology, which makes the fact that Facebook’s AI vision tools are now open source even more important. Improving the current computer vision tech and teaching computers how to recognize objects in images would make searching for a specific image easier.
People with impaired vision could understand what a photo contains because the improved system will be able to tell them this. Facebook already has the technology for blind users on the way. The social networking service aims to provide impaired individuals that are browsing their News Feed with a full description of the content in the photos shared by their friends. Furthermore, Facebook is looking to make the experience even more immersive by having the system describe the content users are swiping their finger across.
On a larger scale, the research team at Facebook hopes to improve the detection and segmentation algorithms to serve other industries as well. One day, developers hope to have the technology applied in areas such as health, commerce, and others. More so, the next challenge would be to apply the technology to video. Currently, the team has been able to make the tools watch videos and understand what’s in them.
You can read more about DeepMask, SharpMask, MultiPathNet and what they can do on Facebook’s FAIR blog.
IMAGE SOURCE: Hijos