Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Last revision Both sides next revision
passthrough [2017/11/26 17:05]
admin
passthrough [2018/01/19 16:53]
admin
Line 181: Line 181:
  
  In this paper, we propose a new method for saliency detection by introducing short connections to the skip-layer structures within the HED architecture. Our framework provides rich multi-scale feature maps at each layer, a property that is critically needed to perform segment detection. ​  In this paper, we propose a new method for saliency detection by introducing short connections to the skip-layer structures within the HED architecture. Our framework provides rich multi-scale feature maps at each layer, a property that is critically needed to perform segment detection. ​
 +
 +https://​arxiv.org/​abs/​1801.05895 Sparsely Connected Convolutional Networks
 +
 +Based on our analysis, we propose a new structure named SparseNets which achieves better performance with fewer parameters than DenseNets and ResNets.