SPCDet: Enhancing Object Detection with Combined Feature Fusing

Haixin Wang, Lintao Wu, Qiongzhi Wu
Proceedings of The Eleventh Asian Conference on Machine Learning, PMLR 101:236-251, 2019.

Abstract

Feature pyramid and feature fusing are widely used in object detection. Using feature pyramid can confront the challenge of scale variation across different objects. Feature fusing imports context information to improve detection performance. Although detecting with feature pyramid and feature fusing has achieved some encouraging results, there are still some limitations owing to the features’ level variance among different layers. In this paper, we exploit that serial-parallel combined feature fusing can enhance object detection. Instead of detecting on the feature pyramid of backbone directly, we fuse different layers from backbone as base features. Then the base features are fed into a U-shape module to build local-global feature pyramid. At last, we use the pyramid to do the multi-scale detection with our combined feature fusing method. We call this one-stage detector SPCDet. It keeps real time speed and outperforms other detectors in trade-off between accuracy and speed.

Cite this Paper

BibTeX
@InProceedings{pmlr-v101-wang19e, title = {SPCDet: Enhancing Object Detection with Combined Feature Fusing}, author = {Wang, Haixin and Wu, Lintao and Wu, Qiongzhi}, booktitle = {Proceedings of The Eleventh Asian Conference on Machine Learning}, pages = {236--251}, year = {2019}, editor = {Lee, Wee Sun and Suzuki, Taiji}, volume = {101}, series = {Proceedings of Machine Learning Research}, month = {17--19 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v101/wang19e/wang19e.pdf}, url = {https://proceedings.mlr.press/v101/wang19e.html}, abstract = {Feature pyramid and feature fusing are widely used in object detection. Using feature pyramid can confront the challenge of scale variation across different objects. Feature fusing imports context information to improve detection performance. Although detecting with feature pyramid and feature fusing has achieved some encouraging results, there are still some limitations owing to the features’ level variance among different layers. In this paper, we exploit that serial-parallel combined feature fusing can enhance object detection. Instead of detecting on the feature pyramid of backbone directly, we fuse different layers from backbone as base features. Then the base features are fed into a U-shape module to build local-global feature pyramid. At last, we use the pyramid to do the multi-scale detection with our combined feature fusing method. We call this one-stage detector SPCDet. It keeps real time speed and outperforms other detectors in trade-off between accuracy and speed.} }
Endnote
%0 Conference Paper %T SPCDet: Enhancing Object Detection with Combined Feature Fusing %A Haixin Wang %A Lintao Wu %A Qiongzhi Wu %B Proceedings of The Eleventh Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Wee Sun Lee %E Taiji Suzuki %F pmlr-v101-wang19e %I PMLR %P 236--251 %U https://proceedings.mlr.press/v101/wang19e.html %V 101 %X Feature pyramid and feature fusing are widely used in object detection. Using feature pyramid can confront the challenge of scale variation across different objects. Feature fusing imports context information to improve detection performance. Although detecting with feature pyramid and feature fusing has achieved some encouraging results, there are still some limitations owing to the features’ level variance among different layers. In this paper, we exploit that serial-parallel combined feature fusing can enhance object detection. Instead of detecting on the feature pyramid of backbone directly, we fuse different layers from backbone as base features. Then the base features are fed into a U-shape module to build local-global feature pyramid. At last, we use the pyramid to do the multi-scale detection with our combined feature fusing method. We call this one-stage detector SPCDet. It keeps real time speed and outperforms other detectors in trade-off between accuracy and speed.
APA
Wang, H., Wu, L. & Wu, Q.. (2019). SPCDet: Enhancing Object Detection with Combined Feature Fusing. Proceedings of The Eleventh Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 101:236-251 Available from https://proceedings.mlr.press/v101/wang19e.html.

Related Material