Scale-Transferrable Object Detection

Peng Zhou, Bingbing Ni, Cong Geng, Jianguo Hu, Yi Xu; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 528-537

Abstract


Scale problem lies in the heart of object detection. In this work, we develop a novel Scale-Transferrable Detection Network (STDN) for detecting multi-scale objects in images. In contrast to previous methods that simply combine object predictions from multiple feature maps from different network depths, the proposed network is equipped with embedded super-resolution layers (named as scale-transfer layer/module in this work) to explicitly explore the inter-scale consistency nature across multiple detection scales. Scale-transfer module naturally fits the base network with little computational cost. This module is further integrated with a dense convolutional network (DenseNet) to yield a one-stage object detector. We evaluate our proposed architecture on PASCAL VOC 2007 and MS COCO benchmark tasks and STDN obtains significant improvements over the comparable state-of-the-art detection models.

Related Material


[pdf]
[bibtex]
@InProceedings{Zhou_2018_CVPR,
author = {Zhou, Peng and Ni, Bingbing and Geng, Cong and Hu, Jianguo and Xu, Yi},
title = {Scale-Transferrable Object Detection},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}