Fat-U-Net: non-contracting U-Net for free-space optical neural networks

Modified U-Net optimised for free-space optical neural networks, achieving up 37x speed-up over GPUs, with minimal performance loss in image segmentation.

Poster presented as part of the Crick BioImage Analysis Symposium 2024.

Permission has been given by authors to upload to Crick Figshare. Copyright remains with the original authors.