Cory's Wiki

Trace: › r-cnns

Introduced in Girshick1), R-CNNs or Regions with Convolutional Neural Networks are an architecture.

The Inception architecture2) combines R-CNNs with strategic use of $1×1$ convolutional layers, and some other techniques (pooling), for a high-performance result.

Is Inception Same as Le et. al.?

FIXME

How is this the Inception architecture3) different from that of the Le et al architecture4)?

  • both seem to use something like local receptive fields combined with pooling.
  • both address larger-scale hardware and network size tradeoffs
    • Inception “goes deeper”
    • High-level explicitly tries to address large-scale inputs, network size. Inspired directly by cogsci
Sparse Layers

FIXME

1)
Girshick et all 2014, Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
2) , 3)
Szegedy et al 2015, Going Deeper With Convolutions
4)
Le et al 2012, Building high-level features using large scale unsupervised learning
Last modified: 2017/11/30 19:46
CC Attribution-Share Alike 4.0 International Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Share Alike 4.0 International