Scribd
Upload
58 views17 pages

Week 5 - Fast RCNN

This document discusses recent developments in object detection using deep learning techniques. It introduces several popular convolutional neural network models for object detection, including RCNN (2014), Fast RCNN (2015), Faster RCNN (2016), YOLO (2016), and SSD (2016). These models apply CNNs to the task of object detection in images in different ways, from classifying object proposals to directly predicting bounding boxes and class probabilities.

Uploaded by

KORNELIS JEMAN
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
58 views17 pages

Week 5 - Fast RCNN

This document discusses recent developments in object detection using deep learning techniques. It introduces several popular convolutional neural network models for object detection, including RCNN (2014), Fast RCNN (2015), Faster RCNN (2016), YOLO (2016), and SSD (2016). These models apply CNNs to the task of object detection in images in different ways, from classifying object proposals to directly predicting bounding boxes and class probabilities.

Uploaded by

KORNELIS JEMAN
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 17

CS4501: Introduction to Computer Vision

Object Detection + Deep Learning


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
deer

cat
Object Detection as Classification
deer?
CNN cat?
background?
Object Detection as Classification
deer?
CNN cat?
background?
Object Detection as Classification
deer?
CNN cat?
background?
Object Detection as Classification
with Sliding Window
deer?
CNN 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

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

Idea: No need to recompute features for every box independently,


Regress refined bounding box coordinates.
https://arxiv.org/abs/1504.08083
https://github.com/sunshineatnoon/Paper-Co
Fast R-CNN. Girshick. ICCV 2015. Fast-RCNN.md
Faster-RCNN

Idea: Integrate the Bounding


Box Proposals as part of the
CNN predictions

https://arxiv.org/abs/1506.01497
Ren et al. NIPS 2015.
YOLO- You Only Look Once

Idea: No bounding
box proposals.
Predict a class and a
box for every location
in a grid.

https://arxiv.org/abs/1506.02640 Redmon et al. CVPR 2016.


YOLO- You Only Look Once

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.

https://arxiv.org/abs/1506.02640 Redmon et al. CVPR 2016.


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. Liu et al. ECCV 2016.
Questions?

17

You might also like