TinyDet: accurately detecting small objects within 1 GFLOPs

Shaoyu Chen, Tianheng Cheng, Jiemin Fang, Qian Zhang, Yuan Li, Wenyu Liu, Xinggang WangScience China Information Sciences 2023 · OpenReview

Abstract

In this study, we propose a series of lightweight detectors named TinyDet. TinyDet is with good performance-computation trade-offs (30.3 mAP with only 991 MFLOPs) and applicable to resource-constrained mobile or edge devices. Besides, TinyDet is superior to other lightweight detectors in small object detection.
BibTeX
@article{chen2023tinydet,
  author = {Shaoyu Chen and Tianheng Cheng and Jiemin Fang and Qian Zhang and Yuan Li and Wenyu Liu and Xinggang Wang},
  title = {{TinyDet: accurately detecting small objects within 1 GFLOPs}},
  journal = {Science China Information Sciences},
  year = {2023},
  url = {https://openreview.net/forum?id=HfqclfCRDV},
}

Loading related content...

Figure