Linear probes demonstrate that feature separability for classification increases monotonically with network depth in Inception v3 and ResNet-50.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2016 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Understanding intermediate layers using linear classifier probes
Linear probes demonstrate that feature separability for classification increases monotonically with network depth in Inception v3 and ResNet-50.