Machine learning
Fully Convolutional Network (FCN)
The Fully Convolutional Network (FCN), introduced by Long, Shelhamer, and Darrell at CVPR 2015, was the first end-to-end deep learning architecture trained to produce dense pixel-wise semantic segmentation maps from images of arbitrary size. By replacing the fully connected layers of a classification CNN with convolutional layers and adding learned upsampling through transposed convolutions and skip connections, FCN enabled the direct prediction of a class label for every pixel in an image, establishing the template for all subsequent segmentation architectures including U-Net and DeepLab.
MethodMind'de açSoonVideoSoon
Tam yöntemi oku
Members only
Sign inSign in with a free account to read this section.
Sources
- Long, J., Shelhamer, E., & Darrell, T. (2015). Fully Convolutional Networks for Semantic Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3431–3440. DOI: 10.1109/CVPR.2015.7298965 ↗
- Shelhamer, E., Long, J., & Darrell, T. (2017). Fully Convolutional Networks for Semantic Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4), 640–651. DOI: 10.1109/TPAMI.2016.2572683 ↗
- Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning (Ch. 9). MIT Press. ISBN: 978-0-262-03561-3