Learning Orientation-aware Distances for Oriented Object Detection
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Geoscience and Remote Sensing"
DOI: 10.1109/tgrs.2023.3278933
Abstract: Oriented object detectors have suffered severely from the discontinuous boundary problem for a long time. In this work, we ingeniously avoid this problem by relating regression outputs to regression target orientations. The core idea of… read more here.
Keywords: regression; learning orientation; one stage; orientation aware ... See more keywords