See Hidden Insight From Transposition: Multiaxis Feature Aggregation for Aerial Object Detection

Recent researches perform aerial object detection from particular perspectives, e.g., small resolution and arbitrary orientations of instances. However, objects with large aspect ratios are actually very common in aerial scenarios, and recent methods seldom carry out their works on the aforementioned topic. In this paper, we propose a large aspect ratio object related method, named See Hidden Insight From Transposition (SHIFT), to elevate the performance of aerial object detection. Firstly, we regard the common convolutional operation as the forward-view feature modeling process, which generates the initially comprehensive descriptors for most aerial objects. This step serves as the foundation for capturing the basic features of different objects. By transposing image features into top- and left-view, our SHIFT can better capture the overall shape and spatial structure of large aspect ratio objects, which may be partially missed or inaccurately represented in the forward-view. Obviously, the top- and left-view features are all strip-like maps, which implicitly express the height and width of objects in image, rather than the texture and appearance. In order to bridge the representational gaps among the aforementioned multi-view features, we further construct an adaptive feature fusion (AFF) module to fuse them in an intelligent way, which models the implicit relationships among these descriptors through the soft attention weights. Our AFF module can be treated as a plug-and-play component, which is end-to-end trainable in the whole detection network. Experimental results on DOTA-v1.0, DOTA-v1.5 and DIOR-R datasets demonstrate that our method achieves superior performance than many recent object detection approaches by a significant margin, including various large aspect ratio related methods.