There are several variants of object detection algorithms. A few algorithms that come with the object detection API are discussed here.
The first work in this series was regions for CNNs proposed by Girshick et al.(https://arxiv.org/pdf/1311.2524.pdf) . It proposes a few boxes and checks whether any of the boxes correspond to the ground truth. Selective search was used for these region proposals. Selective search proposes the regions by grouping the color/texture of windows of various sizes. The selective search looks for blob-like structures. It starts with a pixel and produces a blob at a higher scale. It produces around 2,000 region proposals. This region proposal is less when compared to all the sliding windows possible.
The proposals are resized and passed through a standard CNN architecture such as Alexnet/VGG/Inception/ResNet. The last layer of the CNN is trained with an SVM identifying the object with a no-object...