Christian Eggert
Rainer Lienhart
ABSTRACT
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).
- S. Bell, C. L. Zitnick, K. Bala, and R. Girshick. 2016. Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2874--2883.Google Scholar
- S. Bianco, M. Buzzelli, D. Mazzini, and R. Schettini. 2017. Deep Learning for Logo Recognition. CoRR abs/1701.02620 (2017). http://arxiv.org/abs/1701.02620 Google ScholarDigital Library
- Bernhard E. Boser, Isabelle M. Guyon, and Vladimir N. Vapnik. 1992. A Training Algorithm for Optimal Margin Classifiers. In Proceedings of the Fifth Annual Workshop on Computational Learning Theory (COLT '92). ACM, New York, NY, USA, 144--152. Google ScholarDigital Library
- J. Deng, W. Dong, R. Socher, L. J. Li, Kai Li, and Li Fei-Fei. 2009. ImageNet: A large- scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition. 248--255.Google ScholarCross Ref
- C. Eggert, A. Winschel, D. Zecha, and R. Lienhart. 2016. Saliency-guided Selective Magnification for Company Logo Detection. In 2016 International Conference on Pattern Recognition (ICPR).Google Scholar
- M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. 2010. The Pascal Visual Object Classes (VOC) Challenge. International Journal of Computer Vision 88, 2 (June 2010), 303--338. Google ScholarDigital Library
- R. Girshick. 2015. Fast R-CNN. In IEEE International Conference on Computer Vision. 1440--1448. Google ScholarDigital Library
- R. Girshick, J. Donahue, T. Darrell, and J. Malik. 2014. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. In IEEE Conference on Computer Vision and Pattern Recognition. 580--587. Google ScholarDigital Library
- B. Hariharan, P. Arbelaez, R. Girshick, and J. Malik. 2016. Object Instance Segmen- tation and Fine-Grained Localization using Hypercolumns. IEEE Transactions on Pattern Analysis and Machine Intelligence PP, 99 (2016). Google ScholarDigital Library
- S. Ioffe and C. Szegedy. 2015. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In International Conference on Machine Learning. 448--465. Google ScholarDigital Library
- Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie. 2016. Feature Pyramid Networks for Object Detection. arXiv preprint arXiv:1612.03144 (2016).Google Scholar
- Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C. Berg. 2016. SSD: Single Shot MultiBox Detector. (2016). http://arxiv.org/abs/1512.02325Google Scholar
- G. Oliveira, X. Frazao, A. Pimentel, and B. Ribeiro. 2016. Automatic graphic logo detection via Fast Region-based Convolutional Networks. In 2016 International Joint Conference on Neural Networks (IJCNN). 985--991.Google Scholar
- J. Redmon, S. Divvala, R. Girshick, and A. Farhadi. 2016. You Only Look Once: Unified, Real-Time Object Detection. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 779--788.Google Scholar
- S. Ren, K. He, R. Girshick, and J. Sun. 2016. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence (2016). Google ScholarDigital Library
- S. Romberg, L. G. Pueyo, Lienhart R., and R. van Zwol. 2011. Scalable logo recognition in real-world images. In ACM International Conference on Multimedia Retrieval (ICMR '11). ACM, Article 25, 8 pages. Google ScholarDigital Library
- E. Shelhamer, J. Long, and T. Darrell. 2016. Fully Convolutional Networks for Semantic Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence PP, 99 (2016). Google ScholarDigital Library
- K. Simonyan and A. Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations.Google Scholar
- J. R. R. Uijlings, K. E. A. Sande, T. Gevers, and A. W. M. Smeulders. 2013. Selective Search for Object Recognition. International Journal of Computer Vision 104, 2 (2013), 154--171. Google ScholarDigital Library
- L. Zitnick and P. Dollár. 2014. Edge Boxes: Locating Object Proposals from Edges. In ECCV. European Conference on Computer Vision.Google Scholar
Index Terms
- Improving Small Object Proposals for Company Logo Detection
Recommendations
A hierarchical model to learn object proposals and its applications
Multimedia in technology enhanced learningGenerating class-agnostic object proposals followed by classification has recently become a common paradigm for object detection. Current state-of-the-art approaches typically generate generic objects, which serve as candidates for object classification. ...
Robust object proposals re-ranking for object detection in autonomous driving using convolutional neural networks
Object proposals have recently emerged as an essential cornerstone for object detection. The current state-of-the-art object detectors employ object proposals to detect objects within a modest set of candidate bounding box proposals instead of ...
Learning Multi-Level Features for Breast Mass Detection
ISICDM 2018: Proceedings of the 2nd International Symposium on Image Computing and Digital MedicineIn order to quickly detect masses from mammography images for the early screening of breast cancer, this paper proposes a breast mass detection improved algorithm based on Faster R-CNN. Firstly, we connect multi- level feature maps (conv-4, conv-5) in ...
Comments