U-Net

U-Net is a convolutional neural network that was developed for image segmentation.[1] The network is based on a fully convolutional neural network[2] whose architecture was modified and extended to work with fewer training images and to yield more precise segmentation. Segmentation of a 512 × 512 image takes less than a second on a modern (2015) GPU using the U-Net architecture.[1] [3][4][5]

The U-Net architecture has also been employed in diffusion models for iterative image denoising.[6] This technology underlies many modern image generation models, such as DALL-E, Midjourney, and Stable Diffusion.

  1. ^ a b Ronneberger O, Fischer P, Brox T (2015). "U-Net: Convolutional Networks for Biomedical Image Segmentation". arXiv:1505.04597 [cs.CV].
  2. ^ Shelhamer E, Long J, Darrell T (Nov 2014). "Fully Convolutional Networks for Semantic Segmentation". IEEE Transactions on Pattern Analysis and Machine Intelligence. 39 (4): 640–651. arXiv:1411.4038. doi:10.1109/TPAMI.2016.2572683. PMID 27244717. S2CID 1629541.
  3. ^ Nazem, Fatemeh; Ghasemi, Fahimeh; Fassihi, Afshin; Mehri Dehnavi, Alireza (2021). "3D U-Net: A Voxel-based method in binding site prediction of protein structure". Journal of Bioinformatics and Computational Biology. 19 (2). doi:10.1142/S0219720021500062. PMID 33866960.
  4. ^ Nazem, Fatemeh; Ghasemi, Fahimeh; Fassihi, Afshin; Mehri Dehnavi, Alireza (2023). "A GU-Net-Based Architecture Predicting Ligand–Protein-Binding Atoms". Journal of Medical Signals & Sensors. 13 (1): 1–10. doi:10.4103/jmss.jmss_142_21. PMC 10246592. PMID 37292445.
  5. ^ Nazem, Fatemeh; Ghasemi, Fahimeh; Fassihi, Afshin; Mehri Dehnavi, Alireza (2024). "Deep attention network for identifying ligand-protein binding sites". Journal of Computational Science. 81. doi:10.1016/j.jocs.2024.102368.
  6. ^ Ho, Jonathan (2020). "Denoising Diffusion Probabilistic Models". arXiv:2006.11239 [cs.LG].

Developed by StudentB