CAD: Scale Invariant Framework for Real-Time Object Detection

Huajun Zhou, Zechao Li, Chengcheng Ning, Jinhui Tang; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 760-768

Abstract


Real-time detection frameworks that typically utilize end-to-end networks to scan the entire vision range, have shown potential effectiveness in object detection. However, compared to more accurate but time-consuming frameworks, detection accuracy of existing real-time networks are still left far behind. Towards this end, this work proposes a novel CAD framework to improve detection accuracy while preserving the real-time speed. Moreover, to enhance the generalization ability of the proposed framework, we introduce maxout to approximate the correlation between image pixels and network predictions. In addition, the non-maximum weighted (NMW) is employed to eliminate the redundant bounding boxes that are considered as repetitive detections for the same objects. Extensive experiments are conducted on two detection benchmarks to demonstrate that the proposed framework achieves state-of-the-art performance.

Related Material


[pdf]
[bibtex]
@InProceedings{Zhou_2017_ICCV,
author = {Zhou, Huajun and Li, Zechao and Ning, Chengcheng and Tang, Jinhui},
title = {CAD: Scale Invariant Framework for Real-Time Object Detection},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2017}
}