09.05.2023 Views

pdfcoffee

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

Advanced Convolutional Neural Networks

The next iteration of the R-CNN network was called the Fast R-CNN. The Fast

R-CNN still gets its region proposals from an external tool, but instead of feeding

each region proposal through the CNN, the entire image is fed through the CNN

and the region proposals are projected onto the resulting feature map. Each region of

interest is fed through an Region of Interest (ROI) pooling layer and then to a fully

connected network, which produces a feature vector for the ROI.

ROI pooling is a widely used operation in object detection tasks using convolutional

neural networks. The ROI pooling layer uses max pooling to convert the features

inside any valid region of interest into a small feature map with a fixed spatial extent

of H × W (where H and W are two hyperparameters). The feature vector is then

fed into two fully connected networks, one to predict the class of the ROI and the

other to correct the bounding box coordinates for the proposal. This is illustrated

in Figure 6:

Figure 6: Fast R-CNN network architecture

The Fast R-CNN is about 25x faster than the R-CNN. The next improvement, called

the Faster R-CNN (an implementation can be found at https://github.com/

tensorpack/tensorpack/tree/master/examples/FasterRCNN), removes the

external region proposal mechanism and replaces it with a trainable component,

called the Region Proposal Network (RPN), within the network itself.

[ 144 ]

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!