Dynamic Refinement Network for Oriented and Densely Packed Object Detection

CVPR(2020)

引用 311|浏览252
暂无评分
摘要
Object detection has achieved remarkable progress in the past decade. However, the detection of oriented and densely packed objects remains challenging because of following inherent reasons: (1) receptive fields of neurons are all axis-aligned and of the same shape, whereas objects are usually of diverse shapes and align along various directions; (2) detection models are typically trained with generic knowledge and may not generalize well to handle specific objects at test time; (3) the limited dataset hinders the development on this task. To resolve the first two issues, we present a dynamic refinement network that consists of two novel components, i.e., a feature selection module (FSM) and a dynamic refinement head (DRH). Our FSM enables neurons to adjust receptive fields in accordance with the shapes and orientations of target objects, whereas the DRH empowers our model to refine the prediction dynamically in an object-aware manner. To address the limited availability of related benchmarks, we collect an extensive and fully annotated dataset, namely, SKU110K-R, which is relabeled with oriented bounding boxes based on SKU110K. We perform quantitative evaluations on several publicly available benchmarks including DOTA, HRSC2016, SKU110K, and our own SKU110K-R dataset. Experimental results show that our method achieves consistent and substantial gains compared with baseline approaches. The code and dataset are available at https://github.com/Anymake/DRN_CVPR2020.
更多
查看译文
关键词
dynamic refinement network,densely packed object detection,feature selection module,FSM,dynamic refinement head,DRH,target objects,object-aware manner,extensive annotated dataset,fully annotated dataset,HRSC2016,DOTA,SKU110K-R dataset,receptive fields,oriented bounding boxes
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要