Feature Selective Networks for Object Detection

Main Contributions:

• sub-region attention map and
• aspect ratio attention map for each RoI

 

RoI feature extractor

adopt a 1 × 1 convo- lutional layer to reduce the channel number to Cs and pool the compacted RoI features.

an Nsr Cs -d sub-region attention bank for the entire image by a group of designed shifted convolutional layers.

classify RoIs of different aspect ratios into Nar categories (Nar = 3 demonstrated in Figure 3) and then generate an Nar Cs -d aspect ratio attention bank

 

Sub-Region Attention Bank

Shifted Convolution

• special cases of deformable convolutions
• the 2D offsets of shifted convolutional layers are fixed to (1, 1), (1, 0), (1, −1), ..., (−1, −1), respectively.

Aspect Ratio Attention Bank

• , a 1 × 1 convolutional layer is placed on the convolutional feature map to get the aspect ratio aware components of each spatial position

Attention Maps

Selective RoI Pooling