EfficientViT (IMAGE) Massachusetts Institute of Technology Caption EfficientViT could enable an autonomous vehicle to efficiently perform semantic segmentation, a high-resolution computer vision task that involves categorizing every pixel in a scene so the vehicle can accurately identify objects. Pictured is a still from a demo video showing different colors for categorizing objects. Credit Still courtesy of Song Han, Han Cai et al Usage Restrictions Images are made available to non-commercial entities, press and the general public under a Creative Commons Attribution Non-Commercial No Derivatives license. You may not alter the images provided, other than to crop them to size. A credit line must be used when reproducing images License Original content Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.