Detecting arbitrarily oriented tiny objects poses intense challenges to existing detectors, especially for label assignment. Despite the exploration of adaptive label assignment in recent oriented object detectors, the extreme geometry shape and limited feature of oriented tiny objects still induce severe mismatch and imbalance issues. Specifically, the position prior, positive sample feature, and instance are mismatched, and the learning of extreme-shaped objects is biased and unbalanced due to little proper feature supervision. To tackle these issues, we propose a dynamic prior along with the coarse-to-fine assigner, dubbed DCFL. For one thing, we model the prior, label assignment, and object representation all in a dynamic manner to alleviate the mismatch issue. For another, we leverage the coarse prior matching and finer posterior constraint to dynamically assign labels, providing appropriate and relatively balanced supervision for diverse instances. Extensive experiments on six datasets show substantial improvements to the baseline. Notably, we obtain the state-of-the-art performance for one-stage detectors on the DOTA-v1.5, DOTA-v2.0, and DIOR-R datasets under single-scale training and testing. Codes are available at https://github.com/Chasel-Tsui/mmrotate-dcfl.

翻译：检测任意方向的微小目标对现有检测器提出了严峻挑战，尤其是在标签分配方面。尽管近期定向目标检测器在自适应标签分配方面进行了探索，但定向小目标极端的几何形状和有限的特征仍导致严重的错配与失衡问题。具体而言，位置先验、正样本特征与实例之间存在错配，且由于缺乏适当的特征监督，极端形状目标的学习存在偏差和不均衡。为解决这些问题，我们提出了一种动态先验与由粗到精分配器相结合的方法，简称DCFL。一方面，我们以动态方式建模先验、标签分配和目标表征，以缓解错配问题。另一方面，我们利用粗先验匹配和细后验约束动态分配标签，为不同实例提供适当且相对均衡的监督。在六个数据集上的大量实验表明，该方法相较于基线有显著提升。值得注意的是，在单尺度训练和测试条件下，我们在DOTA-v1.5、DOTA-v2.0和DIOR-R数据集上达到了单阶段检测器的最优性能。代码开源地址为https://github.com/Chasel-Tsui/mmrotate-dcfl。