TransMIN: Transformer-Guided Multi-Interaction Network for Remote Sensing Object Detection

Guangming Xu, Tiecheng Song, Xia Sun, Chenqiang GaoIEEE GRSL 2023 · OpenReview

Abstract

Remote sensing (RS) object detectors based on convolutional neural networks (CNNs) are hard to model global context dependencies. Transformer-based detectors can overcome this problem via global pairwise interactions, but more comprehensive information interactions are not systemically investigated to boost the detection performance. In view of this issue, we propose a transformer-guided multi-interaction network (TransMIN), which uses ResNet50-feature pyramid network (FPN) as the backbone for remote sensing object detection (RSOD). Specifically, we implement local–global feature interactions (LGFIs) by combining convolution and transformer in the residual blocks of ResNet50 to learn complementary features. We implement cross-view feature interactions (CVFIs) via transformers in the pyramid layers of FPN to capture the correlation between reference features (spatial edge priors and channel statistics) and pyramid features. This enhances edge information and suppresses background interference. In the detection head, we adopt a task-interactive sample assigner (TISA) by considering the interactions of classification and localization losses to obtain high-quality predictions. Experiments on two benchmark datasets demonstrate the superior detection performance of TransMIN over state-of-the-art methods.
BibTeX
@article{xu2023transmin,
  author = {Guangming Xu and Tiecheng Song and Xia Sun and Chenqiang Gao},
  title = {{TransMIN: Transformer-Guided Multi-Interaction Network for Remote Sensing Object Detection}},
  journal = {IEEE Geosci. Remote. Sens. Lett.},
  year = {2023},
  url = {https://openreview.net/forum?id=1jFXIlBBaB},
}

Loading related content...

Figure