Conventional convolution, activation, and pooling operations

K rectangular boxes are densely generated on the feature map, and softmax is used to classify activated rectangular boxes and inactive rectangular boxes.

bbox reg returns the activated rectangular box, and the proposal layer generates proposals (selecting the appropriate activated rectangular box)

This layer collects input feature maps and proposals, and extracts proposal feature maps after synthesizing this information.

Since the rectangular frame is divided and maxpool processing is performed on each small square, the output of each activated rectangular frame is of a fixed size and is sent to the subsequent fully connected layer to determine the target category.

Use proposal feature maps to calculate the category of the proposal

At the same time, bounding box regression is performed again to obtain the final precise position of the detection frame.

Embedding information locations into channel attention to find hard-aligned target features

What is channel attention?

CAM divides the backbone network features into two parts and fuses them with the transformer encoder latent features to obtain rich location and association information. Then all features are randomly connected to promote the cross-channel flow of information.

advantage

Aggregating attentional features across scales at the level of transformations

basic detector

A discriminator Cd

Note the hybrid module HAM