2022.4.2

We’ve retrained the AI Computer Vision model and upgraded the internal neural network with a new state-of-the-art architecture, outperforming its predecessor. All UI elements are now detected with higher accuracy, but the largest improvement is related to working with very large tables on 4K screens.

Since WSL 2 can now fully make use of the GPU in Windows 11, the on-premises Windows Computer Vision server has been changed from an installer to a container-based deployment with Docker. The new deployment model is identical to the quick, hassle-free Linux one and includes the latest UiPath Computer Vision Model, boasting significant output quality improvements.

Since Docker is no longer officially supported and shipped with Red Hat Linux 8, the installation process for the Linux Computer Vision server has changed for this specific version of Red Hat to use Podman.

For optimal performance, we recommend upgrading the GPU, as the new model is optimized for the newer Turing architecture GPUs - out of which the T4 is best suited in terms of both cost and performance. These optimizations are not available on the Pascal family of GPUs, so there will be a slight performance gap when running the new model on one.