Pinheiro P H O, Collobert R. Recurrent convolutional neural networks for scene labeling[C]//31st International Conference on Machine Learning (ICML). 2014 (EPFL-CONF-199822).
1. Overview
In this paper, it propose an approach
- consist of a recurrent CNN
- allow to consider a large input context while limiting the capacity of the model
- as the context size increases with the built-in recurrence, the system identifies and corrects its own errors
1.1. Methods
- In Figure 2. The input is a patch and output is the prediction of centerpixel
- For the first time ,the feature is zero map