提出混合锚框旋转检测器，兼顾精度与效率。
HA-RDet: Hybrid Anchor Rotation Detector for Oriented Object Detection
- 每位置仅用一个预设锚框，结合方向感知卷积优化
- DOTA-v1达75.41 mAP，HRSC2016达90.2 mAP
- 兼顾锚框与无锚优势，适合航拍目标检测场景
航拍图像中的定向目标检测面临尺寸和方向变化大等挑战。现有主流方法多采用两阶段或单阶段锚框策略，导致训练时生成大量冗余锚框，计算开销高。而无锚机制虽速度快，但训练样本减少，可能影响精度。为此，本文提出混合锚框旋转检测器（HA-RDet），融合锚框与无锚优点，仅在特征图每个位置使用一个预设锚框，并通过方向感知卷积进行优化。该方法在DOTA-v1上达到75.41 mAP，DIOR-R上65.3 mAP，HRSC2016上90.2 mAP，性能媲美当前最优锚框方法，同时显著降低计算资源消耗。
原文摘要 · Abstract (English)
Oriented object detection in aerial images poses a significant challenge due to their varying sizes and orientations. Current state-of-the-art detectors typically rely on either two-stage or one-stage approaches, often employing Anchor-based strategies, which can result in computationally expensive operations due to the redundant number of generated anchors during training. In contrast, Anchor-free mechanisms offer faster processing but suffer from a reduction in the number of training samples, potentially impacting detection accuracy. To address these limitations, we propose the Hybrid-Anchor Rotation Detector (HA-RDet), which combines the advantages of both anchor-based and anchor-free schemes for oriented object detection. By utilizing only one preset anchor for each location on the feature maps and refining these anchors with our Orientation-Aware Convolution technique, HA-RDet achieves competitive accuracies, including 75.41 mAP on DOTA-v1, 65.3 mAP on DIOR-R, and 90.2 mAP on HRSC2016, against current anchor-based state-of-the-art methods, while significantly reducing computational resources.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。