References

Fully convolutional networks for semantic segmentation

Jonathan Long, Evan Shelhamer, & Trevor Darrell (2015)

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3431-3440.

DOI: https://doi.org/10.1109/cvpr.2015.7298965

Abstract. Introduces fully convolutional networks (FCNs), which replace fully connected layers with 1×1 convolutions and add upsampling layers to produce dense pixel-level predictions. FCNs established the template for modern semantic segmentation architectures.

Tags: cnn segmentation fcn

This site is currently in Beta. Contact: Chris Paton

Textbook of Usability · Textbook of Digital Health

Auckland Maths and Science Tutoring

AI tools used: Claude (research, coding, text), ChatGPT (diagrams, images), Grammarly (editing).