Facebook's SlowFast video classifier AI was inspired by primate eyes

Primates' retinal ganglion cells receive visual info from photoreceptors that they then transmit from the eye to the brain. But not all cells are created equal -- an estimated 80% operate at low frequency and recognize fine details, while about 20% respond to swift changes. This biological dichotomy inspired scientists at Facebook AI Research to pursue what they call SlowFast. It's a machine learning architecture for video recognition that they claim achieves "strong performance" for both action classification and detection in footage. An implementation in Facebook's PyTorch framework -- PySlowFast -- is available on GitHub, along with trained models. As the research team points out in a preprint paper, slow motions occur statistically more often than fast motions, and the recognition of semantics like colors, textures, and lighting can be refreshed slowly without compromising accuracy.