Skip to main content

> ML_LITERATURE // RONNEBERGER-2015-U-NET-CONVOLUTIONAL-NETWORKS-BIOMEDICAL-SEGMENTATION_v1.0

U-Net: Convolutional Networks for Biomedical Image Segmentation

Olaf Ronneberger, Philipp Fischer, Thomas Brox · International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) (2015)

seminal-architecture2015industry-standardthirdPartyReproduced
DOI: 10.1007/978-3-319-24574-4_28Back to Literature

Principal Contribution

Designed an encoder-decoder architecture with dense skip connections transferring high-resolution feature maps across corresponding contracting and expanding levels.

Operational Relevance

Serves as qualified reference for implementing task-image-segmentation in production systems.

Assumptions

  • Underlying spatio-temporal continuity and domain distributional stability hold

Limitations

  • Performance scaling and computational footprint depend on receptive field depth, sequence length, and resolution

Connected Algorithms, Architectures & Tools

Related Algorithms:
Related Architectures:
Implementing Libraries: