Abstract
Human has well demonstrated its cognitive consistency over image transformations such as flipping and scaling. In order to learn from human’s visual perception consistency, researchers find out that convolutional neural network’s capacity of discernment can be further elevated via forcing the network to concentrate on certain area in the picture in accordance with the human natural visual perception. Attention heatmap, as a supplementary tool to reveal the essential region that the network chooses to focus on, has been developed and widely adopted by CNNs. Based on this regime of visual consistency, we propose a novel end-to-end trainable CNN architecture with multi-scale attention consistency. Specifically, our model takes an original picture and its flipped counterpart as inputs, and then send them into a single standard Resnet with additional attention-enhanced modules to generate a semantically strong attention heatmap. We also compute the distance between multi-scale attention heatmaps of these two pictures and take it as an additional loss to help the network achieve better performance. Our network shows superiority on the multi-label classification task and attains compelling results on the WIDER Attribute Dataset.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhang, M.L., Zhou, Z.H.: A review on multi-label learning algorithms. IEEE Trans. Knowl. Data Eng. 26(8), 1819–1837 (2013)
Cao, Y., Wang, Q.-F., Huang, K., Zhang, R.: Improving image caption performance with linguistic context. In: Ren, J., et al. (eds.) BICS 2019. LNCS (LNAI), vol. 11691, pp. 3–11. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-39431-8_1
Gao, Z., Liu, D., Huang, K., Huang, Y.: Context-aware human activity and smartphone position-mining with motion sensors. Remote Sens. 11(21), 2531 (2019)
Lavie, N.: Distracted and confused? Selective attention under load. Trends Cogn. Sci. 9(2), 75–82 (2005)
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In Proceedings of the CVPR, pp. 2921–2929 (2016)
Desimone, R., Duncan, J.: Neural mechanisms of selective visual attention. Ann. Rev. Neurosci. 18(1), 193–222 (1995)
Guo, H., Zheng, K., Fan, X., Yu, H., Wang, S.: Visual attention consistency under image transforms for multi-label image classification. In: Proceedings of the CVPR, pp. 729–739 (2019)
Stollenga, M.F., Masci, J., Gomez, F., Schmidhuber, J.: Deep networks with internal selective attention through feedback connections. In: Advances in Neural Information Processing Systems, pp. 3545–3553 (2014)
Li, X., Zhao, F., Guo, Y.: Multi-label image classification with a probabilistic label enhancement model. In: UAI, vol. 1, p. 3 (2014)
Cabral, R., De la Torre, F., Costeira, J.P., Bernardino, A.: Matrix completion for weakly-supervised multi-label image classification. IEEE Trans. Pattern Anal. Mach. Intell. 37(1), 121–135 (2014)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the CVPR, pp. 7132–7141 (2018)
Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_1
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the CVPR, pp. 770–778 (2016)
Dembczynski, K., Kotlowski, W., Hüllermeier, E.: Consistent multilabel ranking through univariate losses. arXiv preprint arXiv:1206.6401 (2012)
Li, D., Chen, X., Huang, K.: Multi-attribute learning for pedestrian attribute recognition in surveillance scenarios. In: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), pp. 111–115 (2015)
Park, J., Woo, S., Lee, J.Y., Kweon, I.S.: BAM: Bottleneck attention module. arXiv preprint arXiv:1807.06514 (2018)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Proceedings of the CVPR, pp. 248–255(2009)
Li, Y., Huang, C., Loy, C.C., Tang, X.: Human attribute recognition by deep hierarchical contexts. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 684–700. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46466-4_41
Guo, H., Fan, X., Wang, S.: Human attribute recognition by refining attention heat map. Pattern Recogn. Lett. 94, 38–45 (2017)
Zhu, F., Li, H., Ouyang, W., Yu, N., Wang, X.: Learning spatial regularization with image-level supervisions for multi-label image classification. In: Proceedings of the CVPR, pp. 5513–5522 (2017)
Sarafianos, N., Xu, X., Kakadiaris, I.A.: Deep imbalanced attribute classification using visual attention aggregation. In: Proceedings of the ECCV, pp. 680–697 (2018)
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
Acknowledgement
This study was funded by National Natural Science Foundation of China under no. 61876154, 61876155, and U1804159; Natural Science Foundation of Jiangsu Province BK20181189 and BK20181190; Key Program Special Fund in XJTLU under no. KSF-A-10, KSF-A-01, KSF-P-02, KSF-E-26 and KSF-T-06; and XJTLU Research Development Fund RDF-16-02-49 and RDF-16-01-57.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, H., Jin, X., Wang, Q., Huang, K. (2020). Multi-scale Attention Consistency for Multi-label Image Classification. In: Yang, H., Pasupa, K., Leung, A.CS., Kwok, J.T., Chan, J.H., King, I. (eds) Neural Information Processing. ICONIP 2020. Communications in Computer and Information Science, vol 1332. Springer, Cham. https://doi.org/10.1007/978-3-030-63820-7_93
Download citation
DOI: https://doi.org/10.1007/978-3-030-63820-7_93
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63819-1
Online ISBN: 978-3-030-63820-7
eBook Packages: Computer ScienceComputer Science (R0)