Visual Learning and Recognition: Difference between revisions

Visual Learning and Recognition (view source)

372 bytes added , 24 September 2020

5,321

edits

@@ Line 138: / Line 138: @@
 * FC/ReLu
 * FC/Normalization/Loss
+===VGGNet===
+ILSVRC 2014 2nd place
+This is a sequence of deeper networks trained progressively.
+They replace large receptive fields with successive 3x3 conv + ReLU layers.
+A single 7x7 conv layer with C-dim input and C-dim output would need <math>49 \times C^2</math> weights.
+Three <math>3\times 3</math> conv layers only need <math>27 \times C^2</math> weights.
 ==Will be on the exam==