*4.6. Disscusion*

In this section, the experimental settings and results are introduced. First, the adopted DOTA and UAVB dataset are introduced, including their amounts of training/testing images and the distribution of each category samples. Second, implement details are represented, including the input size, crop mechanism of large images, parameter initialization and optimization method and hardware/software platform. Finally, both quantitative and visualized comparison are represented, the results show that under the equal conditions MB-RPN outperform other similar methods.

#### **5. Conclusions**

In this paper, a multi-scale balanced sampling approach for detecting small objects in complex scenes is proposed. With multi-scale positive sampling method, more small objects is able to be included in the network training process. With the balanced negative sampling method, the diversity of negative samples is ensured. Experimental results shows that compare with other similar methods, this approach acquire better performances on the images with small objects and large scale variant objects.

**Author Contributions:** Conceptualization, H.Y.; methodology, H.Y., J.G.; software, H.Y.; validation, H.Y.; writing—original draft preparation, H.Y.; writing—review and editing, D.C.; supervision, D.C.; funding acquisition, D.C. and J.G. All authors have read and agreed to the published version of the manuscript.

**Funding:** This research was funded by Beijing Municipal Natural Science Foundation (4182031).

**Conflicts of Interest:** The authors declare no conflict of interest.
