DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection
This addresses the problem of detecting rotated objects in aerial imagery for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles oriented object detection by proposing DAFNe, a one-stage anchor-free model that introduces an orientation-aware center-ness function and center-to-corner prediction strategy, resulting in outperforming previous one-stage anchor-free models on datasets like DOTA 1.0, DOTA 1.5, and UCAS-AOD, and matching the best on HRSC2016.
We present DAFNe, a Dense one-stage Anchor-Free deep Network for oriented object detection. As a one-stage model, it performs bounding box predictions on a dense grid over the input image, being architecturally simpler in design, as well as easier to optimize than its two-stage counterparts. Furthermore, as an anchor-free model, it reduces the prediction complexity by refraining from employing bounding box anchors. With DAFNe we introduce an orientation-aware generalization of the center-ness function for arbitrarily oriented bounding boxes to down-weight low-quality predictions and a center-to-corner bounding box prediction strategy that improves object localization performance. Our experiments show that DAFNe outperforms all previous one-stage anchor-free models on DOTA 1.0, DOTA 1.5, and UCAS-AOD and is on par with the best models on HRSC2016.