Previewer For Multi-Scale Object Detector
Keywords
Convolutional Neural Networks; Object Detection; Receptive Field
Abstract
Most multi-scale detectors face a challenge of small-size false positives due to the inadequacy of low-level features, which have small receptive field sizes and weak semantic capabilities. This paper demonstrates independent predictions from different feature layers on the same region is beneficial for reducing false positives. We propose a novel light-weight previewer block, which previews the objectness probability for the potential regression region of each prior box, using the stronger features with larger receptive fields and more contextual information for better predictions. This previewer block is generic and can be easily implemented in multi-scale detectors, such as SSD, RFBNet and MS-CNN. Extensive experiments are conducted on PASCAL VOC and KITTI pedestrian benchmark to show the superiority of the proposed method.
Publication Date
10-15-2018
Publication Title
MM 2018 - Proceedings of the 2018 ACM Multimedia Conference
Number of Pages
265-273
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1145/3240508.3240544
Copyright Status
Unknown
Socpus ID
85058240499 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85058240499
STARS Citation
Fu, Zhihang; Jin, Zhongming; Qi, Guo Jun; Shen, Chen; and Jiang, Rongxin, "Previewer For Multi-Scale Object Detector" (2018). Scopus Export 2015-2019. 9539.
https://stars.library.ucf.edu/scopus2015/9539