Abstract
Multiple-label image classification is a kind of supervised learning approach, in which each image can belong to the set of multiple classes. The area of multiple-label image classification increases in recent years, in the field of machine learning. Multiple-label image classification has created significant scope from research people and it has been employed in an image labeling and object prediction tasks. Many conventional machine learning algorithms used for multiple-label image prediction by using relationship between objects in the image, co-occurrence objects, and rank between multiple instances in an image. Deep ConvNet architectures have proved increasing classification performance in image object classification in recent time. This study presents the task of multiple-label classification, the various literatures in area of multiple-label image classification using deep ConvNet architecture, also provides evaluation measures and performs a comparative analysis of the architecture models on PASCAL VOC dataset and various future challenges in the multiple-label image area.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wei, Y., Xia, W., Lin, M., Huang, J., Ni, B., Dong, J., Zhao, Y., Yan, S.: HCP: A flexible CNN framework for multi-label image classification. IEEE Trans. Pattern Anal. Mach. Intell. (2015)
O’Shea, K., Nash, R.: An introduction to convolutional neural networks. arXiv:1511.08458v2. Dec (2015)
Wang, J., Yang Y et al.: CNN-RNN: a unified framework for multiple-label image classification. arxiv:1604.04573. (2016)
Liu, Y., Sheng, L. et al. Multiple-label image classification via knowledge distillation fromweakly-supervised detection. arXiv:1809.05884v2. Feb (2019)
Devkar, R., Shiravale, S.: A survey on multiple-label classification for images. Int. J. Comput. Appl. 162(8), 39–42 (2017)
Yang, H., Zhou, J.T., Cai, J.: Improving multiple-label learning with missing labels by structured semantic correlations. In: European conference on computer vision, 835–851 (2016)
Zhang, J., Wu, Q., Shen, C., Zhang, J., Lu, J.: Multi-label image classification with regional latent semantic dependencies. IEEE Trans. Multimedia 99 1–11 (2018)
van de Sande Koen, E.A., Uijlings, J.R.R., Gevers, T., Smeulders, A.W.M.: 2011. Segmentation as selective search for object recognition. In IEEE International Conference on Computer Vision. 1879–1886
Liu, F., Xiang, T., Hospedales, T.M., Yang, W., Sun, C.: Semantic regularisation for recurrent image annotation. In: IEEE conference on computer vision and pattern recognition. 2872–2880 (2017)
Sermanet, P., Eigen, D., Zhang, X. et al.: Integrated recognition, localization and detection using convolutional networks. arXiv:1312.6229v4. Feb (2014)
Wang, Q., Jia, N. et al.: A baseline for multiple-label image classification using an ensemble of deep convolutional neural networks. arXiv:1811.08412v2 [cs.CV] 16 Feb (2019)
Yu, W.J., Chen, Z.D., Luo, X., Liu, W., Xu, X.S.: DELTA: a deep dual-stream network for multi-label image classification. Pattern Recognition (2019)
Hua, Y., Mou, L., Zhu, X.X.: Recurrently exploring class-wise attention in a hybrid convolutional and bidirectional LSTM network for multi-label aerial image classification. ISPRS J. Photogrammetry Remote Sens. (2019)
Han, D., Liu, Q., Fan. W.: A new image classification method using CNN transfer learning and web data augmentation. Expert Syst. Appl. (2018)
Zhuang, N., Yan, Y., Chen, S., Wang, H., Shen, C.: Multi-label learning based deep transfer neural network for facial attribute classification. Pattern Recogn. (2018)
Niu, Y., Lu, Z., Wen, J.R., Xiang, T., Chang, S.F.: Multi-modal multi-scale deep learning for large-scale image annotation. IEEE Trans. Image Process. (2018)
Oquab, M., Bottou, L., Laptev, I., Sivic, J.: Learning and transferring mid-level image representations using convolutional neural networks. In: IEEE conference on computer vision and pattern recognition, Jun 2014, Columbus, OH, United States. (2014)
Sharif Razavian, A., Azizpour H. et al.: CNN features off-the-shelf: an astounding baseline for recognition. IEEE Explore (2014)
Song, L., Liu, J., et al.: A deep multiple-modal CNN for multiple-instance multiple-label image classification. IEEE Trans. Image Process. 27(12) (December 2018)
Zhu, J., Liao, S., Lei, Z., Li, S.Z.: Multi-label convolutional neural network based pedestrian attribute classification. Image Vis. Comput. (2017)
Wang, M., Luo, C., Hong, R., Tang, J., Feng, J.: Beyond object proposals: random crop pooling for multi-label image recognition. IEEE Trans. Image Process. (2016)
Yao, C., Sun, P., Zhi, R., Shen, Y.: Learning coexistence discriminative features for multi-class object detection. IEEE Explore (2018)
Yu, Q., Wang, J., Zhang, S., Gong, Y., Zhao, J.: Combining local and global hypotheses in deep neural network for multi-label image classification. Neurocomputing (2017)
Zhang, G., Chen, L., Ding, Y.: A multi-label classification model using convolutional netural networks. In: 2017 29th Chinese control and decision conference (CCDC) (2017)
Vallet, A., Sakamoto, H.: A multiple-label convolutional neural network for automatic image annotation. J. Inf. Process. 23(6), 767–775 (2015)
Zhang, M.L., Wu, L.: Lift: multi-label learning with label-specific features. IEEE Trans. Pattern Anal. Mach. Intell. (2015)
Li, Y., Song, Y. et al.: Improving pairwise ranking for multiple-label image classification. IEEE Explore (2017)
Jiang, A., Wang, C., Zhu, Y.: Calibrated rank-SVM for multi-label image categorization. In: 2008 IEEE international joint conference on neural networks (IEEE world Congress on Computational Intelligence), (2008)
Ye, C., Wu, J., Sheng, V.S., Zhao, P., Cui, Z.: Multi-label active learning with label correlation for image classification. In: 2015 IEEE international conference on image processing (ICIP), (2015)
Wang, S., Raju, A. et al.: Deep learning based multiple-label classification for surgical tool presence detection in laparoscopic videos. IEEE Explore (2017)
Dong, M., Pang, K., Wu, Y., Xue, J.H., Hospedales, T., Ogasawara, T.: Transferring CNNS to multi-instance multi-label classification on small datasets. In: 2017 IEEE international conference on image processing (ICIP) (2017)
Lee, S.J., Chen, T., Yu, L., Lai, C.H.: Image classification based on the boost convolutional neural network. IEEE Explore (2018)
Wu, Q., Tan, M., Song, H., Chen, J., Ng, M.K.: ML-forest: a multilabel tree ensemble method for multi-label classification. IEEE Trans. Knowl. Data Eng. (2016)
Zhang, L., Shah, S.K., Kakadiaris, I.A.: Hierarchical multi-label classification using fully associative ensemble learning. Pattern Recogn. (2017)
Lee, S.J., Chen, T. et al.: Image classification based on the boost convolutional neural network. IEEE Access, December (2017)
Shaikh Akib Shahriyar, Kazi Md. Rokibul Alam, Sudipta Singha Roy, Yasuhiko Morimoto.: An approach for multi label image classification using single label convolutional neural network. In: 2018 21st international conference of computer and information technology (ICCIT) (2018)
Oquab, M., Bottou, L., Laptev, I., Sivic, J.: 6 Learning and transferring mid-level image representations using convolutional neural networks. In: IEEE conference on computer vision and pattern recognition, 1717–1724 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
James, S.J., Lakshmi, C. (2020). A Study: Multiple-Label Image Classification Using Deep Convolutional Neural Network Architectures. In: Dash, S., Lakshmi, C., Das, S., Panigrahi, B. (eds) Artificial Intelligence and Evolutionary Computations in Engineering Systems. Advances in Intelligent Systems and Computing, vol 1056. Springer, Singapore. https://doi.org/10.1007/978-981-15-0199-9_65
Download citation
DOI: https://doi.org/10.1007/978-981-15-0199-9_65
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-0198-2
Online ISBN: 978-981-15-0199-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)