Few-example Logo Detection with Model Refinement

Logo detection is a laborious but strong practicality task that has a variety of technology applications. Since the fundamental of state-of-the-art detectors, large-scale annotated datasets, is cost-consuming, few-example logo detection is imperative and thought-provoking. In this paper, a three-stage Few-example Logo Detection Refined System (FLDRS) is proposed to detect logo with a few annotated samples. Specifically, the proposed detector is first initialized using large-scale generic target detection dataset with annotations, such as ImageNet, then further updated with large amount of synthetic logo images, and finally refined with a few annotated real examples. To make synthetic data more closer to real scene, a copy-paste-blend strategy is also presented in our model which not only characterizes many kinds of possible logo transformations but also takes the environment attribute of the logo type into consideration. The superior performance in FlickLogo32 dataset demonstrates the efficiency of the proposed FLDRS.

[1]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Forrest N. Iandola,et al.  DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer , 2015, ArXiv.

[3]  Raimondo Schettini,et al.  Deep Learning for Logo Recognition , 2017, Neurocomputing.

[4]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[5]  Bernardete Ribeiro,et al.  Automatic graphic logo detection via Fast Region-based Convolutional Networks , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[6]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[7]  Olivier Buisson,et al.  Logo retrieval with a contrario visual query expansion , 2009, ACM Multimedia.

[8]  Tao Xiang,et al.  Learning to Compare: Relation Network for Few-Shot Learning , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[9]  Shaogang Gong,et al.  Deep Learning Logo Detection with Data Expansion by Synthesising Context , 2016, 2017 IEEE Winter Conference on Applications of Computer Vision (WACV).

[10]  Richard S. Zemel,et al.  Prototypical Networks for Few-shot Learning , 2017, NIPS.

[11]  Haojie Li,et al.  Region-based CNN for Logo Detection , 2016, ICIMCS.

[12]  Patrick Pérez,et al.  Poisson image editing , 2003, ACM Trans. Graph..

[13]  Gregory R. Koch,et al.  Siamese Neural Networks for One-Shot Image Recognition , 2015 .

[14]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Qiang Wu,et al.  LOGO-Net: Large-scale Deep Logo Detection and Brand Recognition with Deep Region-based Convolutional Networks , 2015, ArXiv.

[16]  Oriol Vinyals,et al.  Matching Networks for One Shot Learning , 2016, NIPS.

[17]  Rainer Lienhart,et al.  Scalable logo recognition in real-world images , 2011, ICMR.

[18]  Fei Su,et al.  Graphic logo detection with deep region-based convolutional networks , 2017, 2017 IEEE Visual Communications and Image Processing (VCIP).

[19]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Shaogang Gong,et al.  WebLogo-2M: Scalable Logo Detection by Deep Learning from the Web , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[21]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[22]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.