Abstract
State-of-the-art convolutional neural networks (CNNs) on sketch classification cannot balance the expression ability of final feature vectors and the problems of gradient vanishing and network degradation. In order to improve the classification accuracy, we design a mixed attention dense network for sketch classification. According to the sparse characteristics of the sketch, this network uses overlapping pooling of a large size. In addition, dense blocks are added on the top of the middle convolutional layers to achieve feature reuse. Specifically, in order to extract more representative local, detail information, mixed attention is applied in the dense blocks. Finally, the center loss is combined with the softmax cross entropy loss to improve the classification accuracy. Through experiments, we compare our model with several state-of-the-art methods on the TU-Berlin dataset, and the experimental results demonstrate the effectiveness of our model.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Eitz M, Hays J, Alexa M (2012) How do humans sketch objects? ACM Trans Graph 31(4):44.1–44.10
Eyiokur Fİ, Yaman D, Ekenel HK (2018) Sketch classification with deep learning models. In: 26th Signal processing and communications applications conference, pp 1–4
Zhang JH, Chen YL, Li L et al (2018) Context-based sketch classification. In: Proceedings of the Joint Symposium on Computational Aesthetics and Sketch-Based Interfaces and Modeling and Non-Photorealistic Animation and Rendering, pp 1–10
Yu Q, Yang YX, Song YZ et al (2015) Sketch-a-net that beats humans. In: British machine vision conference
Yu Q, Yang YX, Liu F, Song YZ, Xiang T, Hospedales TM (2017) Sketch-a-net: A deep neural network that beats humans. Int J Comput Vis 122(3):411–425
He KM, Zhang XY, Ren SQ et al (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition, pp 770–778
Huang G, Liu Z, Maaten LVD (2017) Densely connected convolutional networks. In: 2017 IEEE conference on computer vision and pattern recognition, pp 2261–2269
Sutherland IE (1964) Sketch pad a man-machine graphical communication system. Proceedings of the SHARE Design Automation Workshop, In, pp 329–346
Saavedra JM, Barrios JM, Orand S (2015) Sketch based image retrieval using learned keyshapes. British Machine Vision Conference, pp 164:1–164.11
Li K, Pang KY, Song YZ et al (2016) Fine-grained sketch-based image retrieval: the role of part-aware attributes. In: 2016 IEEE winter conference on applications of computer vision, pp 1–9
Qi YG, Song YZ, Zhang HG et al (2016) Sketch-based image retrieval via Siamese convolutional neural network [A]. In: 2016 IEEE international conference on image processing, pp 2460–2464
Wang F, Kang L, Li Y (2015) Sketch-based 3D shape retrieval using convolutional neural networks. In: In: 2015 IEEE conference on computer vision and pattern recognition, pp 1875–1884
Huang Z, Fu HB, Lau RWH (2014) Data-driven segmentation and labeling of freehand sketches. ACM Trans Graph 33(6):175.1–175.10
Sun ZB, Wang CH, Zhang LQ et al (2012) Free hand-drawn sketch segmentation. In: European Conference on Computer Vision, pp 626–639
Li K, Pang KY, Song JF et al (2018) Universal sketch perceptual grouping. In: European Conference on Computer Vision, pp 593–609
Li L, Fu HB, Tai CL (2018) Fast sketch segmentation and labeling with deep learning. IEEE Comput Graph Appl 39(2):38–51
Sarvadevabhatla RK, Babu RV (2015) Freehand sketch recognition using deep features. arXiv preprint arXiv:1502.00254
Yang YX, Hospedales TM (2015) Deep neural networks for sketch recognition. arXiv preprint arXiv:1501.07873v1
Sert M, Boyac E (2019) Sketch recognition using transfer learning. Multimed Tools Appl 78:17095–17112
Zhang H, She P, Liu Y, Gan J, Cao X, Foroosh H (2019) Learning structural representations via dynamic object landmarks discovery for sketch recognition and retrieval. IEEE Trans Image Process 28(9):4486–4499
Shi Y, Wang K (2020) Sketch recognition based on deformable convolutional network. Computer Science Engineering 6(2):2456–1843
Zhang K, Luo W, Ma L et al (2019) Cousin network guided sketch recognition via latent attribute warehouse. In: Proceedings of the AAAI conference on artificial intelligence, pp 9203–9210
He J-Y, Wu X, Jiang Y-G, Zhao B, Peng Q (2017) Sketch recognition with deep visual-sequential fusion model. In: Proceedings of the 25th ACM international conference on multimedia, pp 448–456
Zhang X, Huang Y, Zou Q, Pei Y, Zhang R, Wang S (2020) A hybrid convolutional neural network for sketch recognition. Pattern Recognition Letters 130:73–82
Kong N, Hou H, Bai Z et al (2019) Lightweight neural network for sketch recognition on mobile phones. In: 5th EAI international summit, pp 428–439
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Proces Syst 25:1–9
Wen YD, Zhang KP, Li ZF et al (2016) A discriminative feature learning approach for deep face recognition. In: European Conference on Computer Vision, pp 499–515
Schneider RG, Tuytelaars T (2014) Sketch classification and classification-driven analysis using fisher vectors. ACM Trans Graph 33(6):174.1–174.9
Seddati O, Dupont S, Mahmoudi S (2015) DeepSketch: deep convolutional neural networks for sketch recognition and similarity search. In: 13th international workshop on content-based multimedia indexing, pp 1–6
Seddati O, Dupont S, Mahmoudi S (2016) DeepSketch 2: deep convolutional neural networks for partial sketch recognition. In: 14th international workshop on content-based multimedia indexing, pp 1–6
Wang XX, Chen XJ, Zha ZJ (2018) Sketchpointnet: a compact network for robust sketch recognition. In: 2018 25th IEEE international conference on image processing, pp 2994–2998
Woo S, Park J, Lee JY et al (2018) CBAM: convolutional block attention module. In: European Conference on Computer Vision, pp 3–19
Acknowledgments
This study was supported by the Open Research Fund of the National Engineering Research Center for Agro-Ecological Big Data Analysis & Application, Anhui University (No. A201903), the National Natural Science Foundation of China (No. 61772032; 61672032) and the National Key R&D Project (SQ2018YFC080102).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhu, M., Chen, C., Wang, N. et al. Mixed attention dense network for sketch classification. Appl Intell 51, 7298–7305 (2021). https://doi.org/10.1007/s10489-021-02211-x
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-02211-x