Facebook renders public / Open Source its AI software for image recognition
▻https://research.facebook.com/blog/learning-to-segment
The main new algorithms driving our advances are the DeepMask1 segmentation framework coupled with our new SharpMask2 segment refinement module. Together, they have enabled FAIR’s [Facebook AI Research] machine vision systems to detect and precisely delineate every object in an image. The final stage of our recognition pipeline uses a specialised convolutional net, which we call MultiPathNet3, to label each object mask with the object type it contains (e.g. person, dog, sheep). We will return to the details shortly.
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
[...]
In addition, our next challenge will be to apply these techniques to video, where objects are moving, interacting, and changing over time. We’ve already made some progress with computer vision techniques to watch videos and understand and classify what’s in them in real time. Real-time classification could help surface relevant and important Live videos on Facebook, while applying more refined techniques to detect scenes, objects, and actions over space and time could one day allow for real-time narration. We’re excited to continue pushing the state of the art and providing better experiences on Facebook for everyone.
DeepMask: Learning to Segment Object Candidates.
Pedro O. Pinheiro, Ronan Collobert, Piotr Dollár (NIPS 2015)
▻https://arxiv.org/pdf/1506.06204v2.pdf
▻https://arxiv.org/abs/1506.06204
SharpMask: Learning to Refine Object Segments.
Pedro O. Pinheiro, Tsung-Yi Lin, Ronan Collobert, Piotr Dollàr (ECCV 2016)
▻https://arxiv.org/pdf/1603.08695v2.pdf
▻https://arxiv.org/abs/1603.08695
MultiPathNet: A Multipath Network for Object Detection.
Sergey Zagoruyko, Adam Lerer, Tsung-Yi Lin, Pedro O. Pinheiro, Sam Gross, Soumith Chintala, Piotr Dollár (BMVC 2016)
▻https://arxiv.org/pdf/1604.02135v2.pdf
▻https://arxiv.org/abs/1604.02135
#AI #Artificial_Intelligence
#machine_vision #image_recognition