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

@article{Eggert2017ACL,
  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)},
  year={2017},
  pages={421-426}
}
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.

References

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

Similar Papers

Loading similar papers…