Long, Jonathan, Evan Shelhamer, and Trevor Darrell. “Fully convolutional networks for semantic segmentation.” Proceedings of the IEEE Conference on Computer Vision and
Pattern Recognition. 2015. (Citations: 863).
Pattern Recognition. 2015. (Citations: 863).
1 Motivation
Previous works use interpolation to up-sample the output predictions to the same size as the input. Instead, we let the model learn the up-sampling weights.
2 Pipeline
See Fig. Fully convolutional networks are used to take input of arbitrary size and produce correspondingly-sized output. Feature maps are up-sampled using deconvolution.The forward pass of deconvolution is the same as backward pass of standard convolution.
3 Skip Connections
See Fig. We use skip connections to combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate
and detailed segmentations. See results in Fig.
4 References
[1]. http://techtalks.tv/talks/fully-convolutional-networks-for-semantic-segmentation/61606/.