PT-DETR: Small Target Detection Based on Partially-Aware Detail Focus
Bingcong Huo, Zhiming Wang

TL;DR
PT-DETR is a novel small-object detection algorithm for UAV imagery that enhances feature extraction and bounding box accuracy, outperforming RT-DETR with higher mAP and lower complexity.
Contribution
Introduces PADF, MFFF, and Focaler-SIoU modules to improve small object detection in UAV images, with better accuracy and efficiency than existing methods.
Findings
Achieves 1.6% and 1.7% higher mAP on VisDrone2019 dataset.
Reduces computational complexity and parameters compared to RT-DETR.
Demonstrates robustness and effectiveness for small-object detection.
Abstract
To address the challenges in UAV object detection, such as complex backgrounds, severe occlusion, dense small objects, and varying lighting conditions,this paper proposes PT-DETR based on RT-DETR, a novel detection algorithm specifically designed for small objects in UAV imagery. In the backbone network, we introduce the Partially-Aware Detail Focus (PADF) Module to enhance feature extraction for small objects. Additionally,we design the Median-Frequency Feature Fusion (MFFF) module,which effectively improves the model's ability to capture small-object details and contextual information. Furthermore,we incorporate Focaler-SIoU to strengthen the model's bounding box matching capability and increase its sensitivity to small-object features, thereby further enhancing detection accuracy and robustness. Compared with RT-DETR, our PT-DETR achieves mAP improvements of 1.6% and 1.7% on the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
