A closer look: Small object detection in faster R-CNN

  title={A closer look: Small object detection in faster R-CNN},
  author={Christian Eggert and Stephan Brehm and Anton Winschel and Dan Zecha and Rainer Lienhart},
  journal={2017 IEEE International Conference on Multimedia and Expo (ICME)},
Faster R-CNN is a well-known approach for object detection which combines the generation of region proposals and their classification into a single pipeline. In this paper we apply Faster R-CNN to the task of company logo detection. Motivated by the weak performance of Faster R-CNN on small object instances, we perform a detailed examination of both the proposal and the classification stage, examining their behavior for a wide range of object sizes. Additionally, we look at the influence of… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.


Publications referenced by this paper.
Showing 1-10 of 10 references

Similar Papers

Loading similar papers…