Meta makes AI video computing costs plummet by 95%, and AI can guess the original picture even if the picture is half covered
Meta researchers have published a series of new papers on MAE (masked auto-encoder), a system that uses SSL technology (self-supervised learning) to predict missing parts of data and restore missing text, images, video and audio.
The general principle of the MAE system for restoring different types of files is to predict what is missing based on existing information, and then compensate for it with other data.
With this technology, AI may be able to automatically annotate data (ground truth) instead of having to annotate it manually. This means that the learning efficiency of AI models has been greatly improved, which may bring new ideas for the future development of AI models.
I. The essence of intelligence is predictive ability, and SSL technology can improve AI intelligence
The MAE system uses SSL (Self-supervised Learning), a technique in which the annotations used for machine learning originate from the data itself, rather than from manual annotations.
OTHER NEWS
-
- Google camera against the sky AI night scene photo new technology RawNeRF unveiled: perfect noise reduction, but also synthesize 3D view angle
- By 25 Aug,2022
-
- Google Pixel Watch smartwatch price revealed, about 1752 yuan from
- By 21 Sep,2022
-
- Amazon Alexa voice assistant turns into a "salesman" as it answers your questions with ads
- By 19 Sep,2022
-
- The world's largest: LG's 97-inch OLED TV opens for pre-order, priced at over $200,000
- By 15 Sep,2022
-
- First experience Lenovo Yoga smart glasses: can cast 108-inch screen, the core components are fully localized
- By 9 Sep,2022
-
- "Robot furniture" into reality: the bed fell from the sky, the table through the wall out
- By 22 Aug,2022