DCNN
global pooling
fully connected
RGB x 240 x 240 pixels
2048 features x 8 x 8
one-hot class vector
2048 features
DCNN
global pooling
1x1 convo layer
RGB x 240 x 240 pixels
2048 features x 8 x 8
one-hot class vector
food not food not
Slide 24
Slide 24 text
w %$//*ODFQUJPO7
w USBJOFEPOBMMGPPEBOE
BMMOPOGPPEQIPUPT
USBJOJOHJTSFBMMZGBTU
w BWFSBHFQPPMJOH
w OPHMPCBMQPPMJOHMBZFS
BGUFSUSBJOJOH
w VTFSFTVMUJOHIFBUNBQ
GPSDMBTTJpDBUJPO
DCNN
global pooling
1x1 convo layer
RGB x 512 x 512 pixels
2048 features x 14 x 14
one-hot class vector
food not
image food person
test images from https://snappygoat.com/
Slide 30
Slide 30 text
image food person
test images from https://snappygoat.com/
Slide 31
Slide 31 text
$)"--&/(&
Slide 32
Slide 32 text
$-"44*':5)*4
Slide 33
Slide 33 text
No content
Slide 34
Slide 34 text
No content
Slide 35
Slide 35 text
No content
Slide 36
Slide 36 text
No content
Slide 37
Slide 37 text
test images from https://snappygoat.com/
Slide 38
Slide 38 text
test images from https://snappygoat.com/
Slide 39
Slide 39 text
%&.0
Slide 40
Slide 40 text
·ͱΊ
•working on food images is an
interesting challenge!
• food / non-food:
• multi-class classifier is better than two class
• fully-convolutional classifier is better than
multi-class
• multi-class object detection from single-object
training data