Differences

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

Link to this comparison view

structured_receptive_field [2017/03/30 00:49]
127.0.0.1 external edit
structured_receptive_field [2018/11/03 17:26] (current)
admin
Line 52: Line 52:
 We use the scattering network as a generic and fixed initialization of the first layers of a supervised hybrid deep network. We show that early layers do not necessarily need to be learned, providing the best results to-date with pre-defined representations while being competitive with Deep CNNs. We use the scattering network as a generic and fixed initialization of the first layers of a supervised hybrid deep network. We show that early layers do not necessarily need to be learned, providing the best results to-date with pre-defined representations while being competitive with Deep CNNs.
  
 +https://​arxiv.org/​pdf/​1809.06367v1.pdf Scattering Networks for Hybrid Representation
 +Learning
  
 + For supervised learning, we demonstrate
 +that the early layers of CNNs do not necessarily need to be learned, and
 +can be replaced with a scattering network instead. Indeed, using hybrid
 +architectures,​ we achieve the best results with predefined representations
 +to-date, while being competitive with end-to-end learned CNNs.