A DeNoising FPN With Transformer R-CNN for Tiny Object Detection

Abstract

Despite notable advancements in the field of computer vision (CV), the precise detection of tiny objects continues to pose a significant challenge, largely due to the minuscule pixel representation allocated to these objects in imagery data. This challenge resonates profoundly in the domain of geoscience and remote sensing, where high-fidelity detection of tiny objects can facilitate a myriad of applications ranging from urban planning to environmental monitoring. In this article, we propose a new framework, namely, DeNoising feature pyramid network (FPN) with Trans R-CNN (DNTR), to improve the performance of tiny object detection. DNTR consists of an easy plug-in design, DeNoising FPN (DN-FPN), and an effective Transformer-based detector, Trans region-based convolutional neural network (R-CNN). Specifically, feature fusion in the FPN is important for detecting multiscale objects. However, noisy features may be produced during the fusion process since there is no regularization between the features of different scales. Therefore, we introduce a DN-FPN module that utilizes contrastive learning to suppress noise in each level’s features in the top–down path of FPN. Second, based on the two-stage framework, we replace the obsolete R-CNN detector with a novel Trans R-CNN detector to focus on the representation of tiny objects with self-attention. The experimental results manifest that our DNTR outperforms the baselines by at least 17.4% in terms of APvt on the AI-TOD dataset and 9.6% in terms of average precision (AP) on the VisDrone dataset, respectively. Our code will be available at https://github.com/hoiliu-0801/DNTR.

Key Contributions

• Proposed a novel tiny object detection framework DNTR, which combines a DeNoising Feature Pyramid Network (DN-FPN) with a Transformer-based detector (Trans R-CNN).
• Designed an innovative DN-FPN module that utilizes contrastive learning to suppress noise generated during feature fusion across different scales in the feature pyramid network.
• Developed a Transformer-based Trans R-CNN detector that leverages self-attention mechanisms to enhance the representation of tiny objects.
• Conducted extensive experiments on AI-TOD and VisDrone datasets, achieving significant performance improvements of 17.4% in APvt and 9.6% in AP respectively.

Related Links

• Paper PDF
• Code
• Project Page

Citation

If you find this work helpful, please consider citing:

@article{liu2024denoising,
  title={A denoising fpn with transformer r-cnn for tiny object detection},
  author={Liu, Hou-I and Tseng, Yu-Wen and Chang, Kai-Cheng and Wang, Pin-Jyun and Shuai, Hong-Han and Cheng, Wen-Huang},
  journal={IEEE Transactions on Geoscience and Remote Sensing},
  year={2024},
  publisher={IEEE}
}

Recommended citation: Hou-I. Liu, Yu-Wen Tseng, Kai-Cheng Chang, Pin-Jyun Wang, Hong-Han Shuai, and Wen-Huang Cheng. "A denoising fpn with transformer r-cnn for tiny object detection." IEEE Transactions on Geoscience and Remote Sensing (2024).
Download Paper