Improving Small Object Proposals for Company Logo Detection

被引:52
作者
Eggert, Christian [1 ]
Zecha, Dan [1 ]
Brehm, Stephan [1 ]
Lienhart, Rainer [1 ]
机构
[1] Univ Augsburg, Univ Str 6a, D-86199 Augsburg, Germany
来源
PROCEEDINGS OF THE 2017 ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL (ICMR'17) | 2017年
关键词
Object Proposals; Object Detection; Object Recognition; Region Proposal Network; RPN; Small objects; Faster R-CNN; Company Logos; Brand Detection;
D O I
10.1145/3078971.3078990
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Many modern approaches for object detection are two-staged pipelines. The first stage identifies regions of interest which are then classified in the second stage. Faster R-CNN is such an approach for object detection which combines both stages into a single pipeline. In this paper we apply Faster R-CNN to the task of company logo detection. Motivated by its weak performance on small object instances, we examine in detail both the proposal and the classification stage with respect to a wide range of object sizes. We investigate the influence of feature map resolution on the performance of those stages. Based on theoretical considerations, we introduce an improved scheme for generating anchor proposals and propose a modification to Faster R-CNN which leverages higher-resolution feature maps for small objects. We evaluate our approach on the FlickrLogos dataset improving the RPN performance from 0.52 to 0.71 (MABO) and the detection performance from 0.52 to 0.67 (mAP).
引用
收藏
页码:172 / 179
页数:8
相关论文
共 20 条
[1]  
[Anonymous], 2011, P 1 ACM INT C MULT R, DOI DOI 10.1145/1991996.1992021
[2]   Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks [J].
Bell, Sean ;
Zitnick, C. Lawrence ;
Bala, Kavita ;
Girshick, Ross .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :2874-2883
[3]   Deep learning for logo recognition [J].
Bianco, Simone ;
Buzzelli, Marco ;
Mazzini, Davide ;
Schettini, Raimondo .
NEUROCOMPUTING, 2017, 245 :23-30
[4]  
Boser B. E., 1992, Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory, P144, DOI 10.1145/130385.130401
[5]  
Deng J, 2009, PROC CVPR IEEE, P248, DOI 10.1109/CVPRW.2009.5206848
[6]  
Eggert C, 2016, INT C PATT RECOG, P651, DOI 10.1109/ICPR.2016.7899708
[7]  
Everingham Mark, 2010, INT J COMPUT VISION, V88, P303, DOI DOI 10.1007/s11263-009-0275-4
[8]   Fast R-CNN [J].
Girshick, Ross .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :1440-1448
[9]   Rich feature hierarchies for accurate object detection and semantic segmentation [J].
Girshick, Ross ;
Donahue, Jeff ;
Darrell, Trevor ;
Malik, Jitendra .
2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, :580-587
[10]   Object Instance Segmentation and Fine-Grained Localization Using Hypercolumns [J].
Hariharan, Bharath ;
Arbelaez, Pablo ;
Girshick, Ross ;
Malik, Jitendra .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (04) :627-639