Feedback RoI Features Improve Aerial Object Detection
This work addresses object detection challenges in aerial imagery, which is incremental as it enhances existing methods with a feedback module.
The paper tackled the problem of object detection in aerial images by incorporating feedback mechanisms inspired by human vision, resulting in consistent improvements across multiple state-of-the-art methods on datasets like DOTA-v1.0, DOTA-v1.5, and HRSC2016, with efficacy also shown on MS COCO.
Neuroscience studies have shown that the human visual system utilizes high-level feedback information to guide lower-level perception, enabling adaptation to signals of different characteristics. In light of this, we propose Feedback multi-Level feature Extractor (Flex) to incorporate a similar mechanism for object detection. Flex refines feature selection based on image-wise and instance-level feedback information in response to image quality variation and classification uncertainty. Experimental results show that Flex offers consistent improvement to a range of existing SOTA methods on the challenging aerial object detection datasets including DOTA-v1.0, DOTA-v1.5, and HRSC2016. Although the design originates in aerial image detection, further experiments on MS COCO also reveal our module's efficacy in general detection models. Quantitative and qualitative analyses indicate that the improvements are closely related to image qualities, which match our motivation.