MCDet: Multi-Content Collaboration Detector for Multiscale Remote Sensing Object

Wenping Ma, Hao Chen, Hao Zhu, Na Li, Yue Wu, Biao Hou, Licheng Jiao

Abstract

In previous works, powerful convolutional neural network (CNN) backbones are typically used for one- or two-stage detectors to facilitate multicategories object classification. Unfortunately, continuous convolution and pooling operations tend to weaken the detailed information. We propose an end-to-end multi-content collaboration detector (MCDet) to improve object recognition accuracy. First, we summarize the reasons for the disappearance of detailed features in the traditional feature extraction backbone networks and propose a shallow clue refinement (SCR) module, which helps us to retain more critical local detail information in the downsampling process. Second, to receive more suitable contextual information, we design a self-dilating spatial pooling (SSP) module; it adaptively learns a contextual reception field, thereby alleviating the mismatch between the theoretical receptive field of the network design and the practical requirements. Finally, extensive experiments on the NWPU VHR-10 and DIOR datasets have shown that the proposed MCDet significantly improves detection accuracy. Our code is available at https://github.com/Xidian-AIGroup190726/RS-objectdetection-MCDet .
BibTeX
@article{ma2024mcdet,
  author = {Wenping Ma and Hao Chen and Hao Zhu and Na Li and Yue Wu and Biao Hou and Licheng Jiao},
  title = {{MCDet: Multi-Content Collaboration Detector for Multiscale Remote Sensing Object}},
  journal = {IEEE Geosci. Remote. Sens. Lett.},
  year = {2024},
  url = {https://openreview.net/forum?id=WsswsZoL15},
}

Loading related content...

Figure