文献类型：期刊文献

英文题名：Cascade Feature Pyramid Neural Nwtwork for Object Detector

作者：Han, Fei[1]; Zhu, Yu[1]; Huang, Junjian[1]

机构：[1] School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China

年份：2019

外文期刊名：Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019

收录：EI(收录号：20200708158443)

语种：英文

外文关键词：Feature extraction - Object recognition - Semantics - Classification (of information) - Computer vision

摘要：Early object detection networks apply single scale feature to predict the classification and regression. However, the semantic information which is from the low-level features is less than that on the high-level features, and locations of objects on the low-level are more accurate than that on the high-level. Recently, feature pyramid fusion is widely applied by one-stage object detectors (e.g. DSSD, RefineDet), which achieves encouraging results of the object detection, but only simply constructs the feature pyramid according to multi-scale feature maps. In our work, we design a network, called CFPNet, which applies cascade feature pyramid layer (CFP) to predict the classification and regression. CFPNet achieves 80.1% mAP with small input size (320× 320) and 82.0% mAP with large input size (512 × 512), experimenting on PASCAL VOC2007 and PASCAL VOC2012. The network with low dimension input size runs 34 FPS in NVIDIA 1080Ti, which achieves the high accuracy and maintains fast speed. ? 2019 IEEE.