Last Class Convolutional (Neural) Networks Neural Network Architectures Imagenet Today’s Class

Object Detection + Deep Learning
By Buriyev Doston group:224-16

Last Class

• Convolutional (Neural) Networks
• Neural Network Architectures
• Imagenet

Today’s Class

• Object Detection
• The RCNN Object Detector (2014)
• The Fast RCNN Object Detector (2015)
• The Faster RCNN Object Detector (2016)
• The YOLO Object Detector (2016)
• The SSD Object Detector (2016)
• Mask-RCNN (2017)

Object Detection

cat
deer

Object Detection as Classification

CNN
deer?
cat?
background?

Object Detection as Classification

CNN
deer?
cat?
background?

Object Detection as Classification

CNN
deer?
cat?
background?

Object Detection as Classification with Sliding Window

CNN
deer?
cat?
background?

Object Detection as Classification with Box Proposals

Box Proposal Method – SS: Selective Search

Segmentation As Selective Search for Object Recognition. van de Sande et al. ICCV 2011

RCNN

Rich feature hierarchies for accurate object detection and semantic segmentation. Girshick et al. CVPR 2014.
https://people.eecs.berkeley.edu/~rbg/papers/r-cnn-cvpr.pdf

Fast-RCNN

https://arxiv.org/abs/1504.08083
Idea: No need to recompute features for every box independently, Regress refined bounding box coordinates.

Faster-RCNN

https://arxiv.org/abs/1506.01497
Idea: Integrate the Bounding Box Proposals as part of the CNN predictions

YOLO- You Only Look Once

https://arxiv.org/abs/1506.02640
Idea: No bounding box proposals. Predict a class and a
box for every location
in a grid.

YOLO- You Only Look Once

https://arxiv.org/abs/1506.02640
Divide the image into 7x7 cells.
Each cell trains a detector.
The detector needs to predict the object’s class distributions.
The detector has 2 bounding-box predictors to predict
bounding-boxes and confidence scores.

SSD: Single Shot Detector

Idea: Similar to YOLO, but denser grid map, multiscale grid maps. + Data augmentation + Hard negative mining + Other design choices in the network.