Deep Learning for Computer Vision

Combining regression with the sliding window

The classification score is computed for every window in the sliding window approach or the fully convolutional approach to know what object is present in that window. Instead of predicting the classification score for every window to detect an object, each window itself can be predicted with a classification score. Combining all the ideas such as sliding window, scale-space, full convolution, and regression give superior results than any individual approach. The following are the top five localization error rates on the ImageNet dataset achieved by various networks using the regression approach:

The preceding graph shows that the deeper the network, the better the results. For AlexNet, localization ...