作者：Xue Yang，Kun Fu，Hao Sun，Jirui Yang，Zhi Guo，Menglong Yan，Tengfei Zhang，Sun Xian
发布时间：
发布期刊：ICCV
论文全称：R2CNN++: Multi-Dimensional Attention Based Rotation Invariant Detector with Robust Anchor Strategy
**SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects**
论文地址：
代码：*https://github.com/DetectionTeamUCAS/R2CNN-Plus-Plus_Tensorflow*
https://github.com/DetectionTeamUCAS/RetinaNet_Tensorflow_Rotation
*Object detection plays a vital role in natural scene and aerial scene and is full of challenges. Although many advanced algorithms have succeeded in the natural scene,the progress in the aerial scene has been slow due to the complexity of the aerial image and the large degree of freedom of remote sensing objects in scale, orientation, and density. In this paper, a novel multi-category rotation detector is proposed, which can effificiently detect small objects, arbitrary direction objects, and dense objects in complex remote sensing images. Specififically,the proposed model adopts a targeted feature fusion strategy called inception fusion network, which fully considers factors such as feature fusion, anchor sampling, and receptive fifield to improve the ability to handle small objects. Then we combine the pixel attention network and the channel attention network to weaken the noise information and highlight the objects feature. Finally, the rotational object detection algorithm is realized by redefifining the rotating bounding box. Experiments on public datasets including DOTA, NWPU VHR-10 demonstrate that the proposed algorithm signifificantly outperforms state-of-the-art methods. The code and models will be available at https://github.com/DetectionTeamUCAS/R2CNN-Plus-Plus_Tensorflow.*