ReAFFPN: Rotation-equivariant Attention Feature Fusion Pyramid Networks for Aerial Object Detection
This work addresses a domain-specific challenge in aerial object detection by enhancing feature fusion for rotated objects, representing an incremental improvement over existing methods.
The paper tackled the problem of rotation-equivariant feature fusion in aerial object detection by proposing ReAFFPN, which integrates a new Rotation-equivariant Channel Attention into an iterative fusion module, resulting in significantly improved accuracy for Rotation-equivariant Convolutional Networks.
This paper proposes a Rotation-equivariant Attention Feature Fusion Pyramid Networks for Aerial Object Detection named ReAFFPN. ReAFFPN aims at improving the effect of rotation-equivariant features fusion between adjacent layers which suffers from the semantic and scale discontinuity. Due to the particularity of rotational equivariant convolution, general methods are unable to achieve their original effect while ensuring rotation equivariance of the network. To solve this problem, we design a new Rotation-equivariant Channel Attention which has the ability to both generate channel attention and keep rotation equivariance. Then we embed a new channel attention function into Iterative Attentional Feature Fusion (iAFF) module to realize Rotation-equivariant Attention Feature Fusion. Experimental results demonstrate that ReAFFPN achieves a better rotation-equivariant feature fusion ability and significantly improve the accuracy of the Rotation-equivariant Convolutional Networks.