Computer Science ›› 2020, Vol. 47 ›› Issue (2): 83-87.doi: 10.11896/jsjkx.190500077

• Computer Graphics & Multimedia • Previous Articles     Next Articles

Classification Net Based on Angular Feature

WANG Li-hua,DU Ming-hui,LIANG Ya-ling   

  1. (School of Electronics and Information,South China University of Technology,GuangZhou 510641,China)
  • Received:2019-05-17 Online:2020-02-15 Published:2020-03-18
  • About author:WANG Li-hua,born in 1995,postgra-duate.His main research interests include computer vision and deep learning;DU Ming-hui,born in 1964,professor,Ph.D superuisor.His main research interests include signal processing and image processing.
  • Supported by:
    This work was supported by the National Natural Science Foundation of China (61701181), Natural Science Foundation of Guangdong Province, China (2017A030325430) and Science and Technology Program of Guangzhou, China (201707010070).

Abstract: The excellent performance of Convolutional Neural Networks (CNN) in image classification tasks makes CNN models widely used in various fields of computer vision.In addition to the changes in the network structure,a large part of the reason why the accuracy and efficiency of the image classification model increase year by year comes from thenormalization technology and the improvement of the classification loss function.In the face recognition task,with the increasing precision,the classification loss function change from Softmax Loss to Triplet Loss,and from L-Softmax Loss to Arcface Loss,the measurement method develops from geometric measurement to angle measurement.The change of measurement mode is actually a change of feature form,and the feature form changes from general feature to angle feature.The feature points trained on the Mnist dataset using the angle metric loss function are angularly distributed,and the accuracy is higher than the geometric metric.If the angle metric is represented by more direct angular features,the feature points of the same class are linearly distributed after training,and accuracy is also higher than the general angle metric.This makes people wonder whether angle features can be used instead of general features in the CNN classification model.In the CNN classification model,the main structure is often composed of multiple convolutional layers and one or several fully connected layers.Through unifying the normalization operation of the convolutional layer and the fully connected layer,layers in model come to the angular convolutional layers and the angular fully connected layers.On the basis of the common classification network,the convolution layer is replaced by the angle convolution layer,and the full connection layer is replaced by the angle full connection layer,and then an angle classification network composed of angular features can be obtained.The accuracy of the angle classification network constructed on ResNet-32 is 2% higher than that of the original classification network on the Cifar-100 dataset.The validity of the feature in the classification network is demonstrated.

Key words: Angular feature, Convolutional neural networks, Image classification, Loss function, Normalization

CLC Number: 

  • TP183
[1]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6):84-90.
[2]SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].arXiv:1409.1556,2014.
[3]SZEGEDY C,LIU W,JIA Y Q,et al.Going deeper with convolutions[C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Boston,MA,USA:IEEE,2015:1-9.
[4]GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]∥2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus,OH,USA:IEEE,2014:580-587.
[5]GIRSHICK R.Fast R-CNN[C]∥2015 IEEE International Conference on Computer Vision (ICCV).Santiago,Chile:IEEE,2015:1440-1448.
[6]REN S Q,HE K M,GIRSHICK R,et al.Faster R-CNN:to-wards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[7]LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]∥2015 IEEE Confe-rence on Computer Vision and Pattern Recognition (CVPR).Boston,MA,USA:IEEE,2015:3431-3440.
[8]SIMONYAN K,ZISSERMAN A.Two-stream convolutional networks for action recognition in videos[C]∥Advances in Neural Information Processing Systems.2014:568-576.
[9]HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas,NV,USA:IEEE,2016:770-778.
[10]HUANG G,LIU Z,MAATEN L V D,et al.Densely connected convolutional networks[C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2017:4700-4708.
[11]IOFFE S,SZEGEDY C.Batch normalization:Accelerating deep network training by reducing internal covariate shift[J].arXiv:1502.03167,2015.
[12]SALIMANS T,KINGMA D P.Weight normalization:A simple reparameterization to accelerate training of deep neural net-works[C]∥Advances in Neural Information Processing Systems.2016:901-909.
[13]LEI BA J,KIROS J R,HINTON G E.Layer normalization[J].arXiv:1607.06450,2016.
[14]SCHROFF F,KALENICHENKO D,PHILBIN J.FaceNet:a unified embedding for face recognition and clustering[C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Boston,MA,USA:IEEE,2015:815-823.
[15]LIU W,WEN Y,YU Z,et al.Large-margin softmax loss for convolutional neural networks[C]∥ICML.2016:7.
[16]RANJAN R,CASTILLO C D,CHELLAPPA R.L2-constrained softmax loss for discriminative face verification[J].arXiv:1703.09507,2017.
[17]LIU W Y,WEN Y D,YU Z D,et al.SphereFace:deep hypersphere embedding for face recognition[C]∥2017 IEEE Confe-rence on Computer Vision and Pattern Recognition (CVPR).Honolulu,HI:IEEE,2017:212-220.
[18]WANG F,CHENG J,LIU W Y,et al.Additive margin softmax for face verification[J].IEEE Signal Processing Letters,2018,25(7):926-930.
[19]WANG H,WANG Y T,ZHOU Z,et al.CosFace:large margin cosine loss for deep face recognition[C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT:IEEE,2018:5265-5274.
[20]DENG J,GUO J,XUE N,et al.Arcface:Additive angular margin loss for deep face recognition[J].arXiv:1801.07698,2018.
[21]HUANG G B,LEARNED-MILLER E.Labeled faces in the wild:Updates and new reporting procedures:Technical Report UM-CS-2014-003 [R].Massachusetts Amherst,Amherst,MA,USA,2014.
[23]LIU W Y,LIU Z,YU Z D,et al.Decoupled networks[C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT:IEEE,2018:2771-2779.
[1] ZHU Cheng-zhang, HUANG Jia-er, XIAO Ya-long, WANG Han, ZOU Bei-ji. Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism [J]. Computer Science, 2022, 49(8): 113-119.
[2] WU Hong-xin, HAN Meng, CHEN Zhi-qiang, ZHANG Xi-long, LI Mu-hang. Survey of Multi-label Classification Based on Supervised and Semi-supervised Learning [J]. Computer Science, 2022, 49(8): 12-25.
[3] MENG Yue-bo, MU Si-rong, LIU Guang-hui, XU Sheng-jun, HAN Jiu-qiang. Person Re-identification Method Based on GoogLeNet-GMP Based on Vector Attention Mechanism [J]. Computer Science, 2022, 49(7): 142-147.
[4] YANG Jian-nan, ZHANG Fan. Classification Method for Small Crops Combining Dual Attention Mechanisms and Hierarchical Network Structure [J]. Computer Science, 2022, 49(6A): 353-357.
[5] DU Li-jun, TANG Xi-lu, ZHOU Jiao, CHEN Yu-lan, CHENG Jian. Alzheimer's Disease Classification Method Based on Attention Mechanism and Multi-task Learning [J]. Computer Science, 2022, 49(6A): 60-65.
[6] GAO Rong-hua, BAI Qiang, WANG Rong, WU Hua-rui, SUN Xiang. Multi-tree Network Multi-crop Early Disease Recognition Method Based on Improved Attention Mechanism [J]. Computer Science, 2022, 49(6A): 363-369.
[7] WANG Jian-ming, CHEN Xiang-yu, YANG Zi-zhong, SHI Chen-yang, ZHANG Yu-hang, QIAN Zheng-kun. Influence of Different Data Augmentation Methods on Model Recognition Accuracy [J]. Computer Science, 2022, 49(6A): 418-423.
[8] SUN Jie-qi, LI Ya-feng, ZHANG Wen-bo, LIU Peng-hui. Dual-field Feature Fusion Deep Convolutional Neural Network Based on Discrete Wavelet Transformation [J]. Computer Science, 2022, 49(6A): 434-440.
[9] ZHU Xu-dong, XIONG Yun. Study on Multi-label Image Classification Based on Sample Distribution Loss [J]. Computer Science, 2022, 49(6): 210-216.
[10] PENG Yun-cong, QIN Xiao-lin, ZHANG Li-ge, GU Yong-xiang. Survey on Few-shot Learning Algorithms for Image Classification [J]. Computer Science, 2022, 49(5): 1-9.
[11] ZHANG Wen-xuan, WU Qin. Fine-grained Image Classification Based on Multi-branch Attention-augmentation [J]. Computer Science, 2022, 49(5): 105-112.
[12] XU Hua-jie, CHEN Yu, YANG Yang, QIN Yuan-zhuo. Semi-supervised Learning Method Based on Automated Mixed Sample Data Augmentation Techniques [J]. Computer Science, 2022, 49(3): 288-293.
[13] DONG Lin, HUANG Li-qing, YE Feng, HUANG Tian-qiang, WENG Bin, XU Chao. Survey on Generalization Methods of Face Forgery Detection [J]. Computer Science, 2022, 49(2): 12-30.
[14] CHEN Zhi-yi, SUI Jie. DeepFM and Convolutional Neural Networks Ensembles for Multimodal Rumor Detection [J]. Computer Science, 2022, 49(1): 101-107.
[15] HUANG Ying-qi, CHEN Hong-mei. Cost-sensitive Convolutional Neural Network Based Hybrid Method for Imbalanced Data Classification [J]. Computer Science, 2021, 48(9): 77-85.
Full text



No Suggested Reading articles found!