Abstract
Image-text retrieval has always been an important direction in the field of vision-language understanding, which is dedicated to bridging the semantic gap between two modalities. The existing methods are mainly divided into global visual-semantic embedding and local region-word alignment. Although the local region-word alignment method has achieved remarkable results, this method based on fine-grained features often leads to low retrieval efficiency. At the same time, the method based on global embedding lacks extra semantic information, resulting in insufficient accuracy. In this paper, we propose a novel self-supervised visual-semantic embedding network based on local label optimization. Specifically, we generate a label for the entire image-text pair from the local information and use this label to optimize our embedding network, which can not only affect the retrieval efficiency but also significantly improve the retrieval accuracy. Experimental results on two benchmark datasets validate the effectiveness of our method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6077–6086 (2018)
Andrew, G., Arora, R., Bilmes, J.A., Livescu, K.: Deep canonical correlation analysis 28, 1247–1255 (2013)
Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation (2014)
Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database, pp. 248–255 (2009)
Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: VSE++: improving visual-semantic embeddings with hard negatives (2018)
Hardoon, D.R., Szedmák, S., Shawe-Taylor, J.: Canonical correlation analysis: an overview with application to learning methods. Neural Comput. 16(12), 2639–2664 (2004)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions, pp. 3128–3137 (2015). https://doi.org/10.1109/CVPR.2015.7298932
Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123, 32–73 (2016)
Lee, K.H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. arXiv abs/1803.08024 (2018)
Li, C., Deng, C., Li, N., Liu, W., Gao, X., Tao, D.: Self-supervised adversarial hashing networks for cross-modal retrieval, pp. 4242–4251 (2018)
Liu, C., Mao, Z., Liu, A., Zhang, T., Wang, B., Zhang, Y.: Focus your attention: a bidirectional focal attention network for image-text matching. In: Proceedings of the 27th ACM International Conference on Multimedia (2019)
Nam, H., Ha, J.W., Kim, J.: Dual attention networks for multimodal reasoning and matching. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2156–2164 (2017)
Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137–1149 (2015)
Wang, L., Li, Y., Lazebnik, S.: Learning deep structure-preserving image-text embeddings, pp. 5005–5013 (2016)
Wang, Y., et al.: Position focused attention network for image-text matching, pp. 3792–3798 (2019)
Wang, Z., et al.: Camp: cross-modal adaptive message passing for text-image retrieval. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 5763–5772 (2019)
Wen, K., Gu, X., Cheng, Q.: Learning dual semantic relations with graph attention for image-text matching. IEEE Trans. Circuits Syst. Video Technol. 31, 2866–2879 (2021)
Xu, T., et al.: AttnGAN: fine-grained text to image generation with attentional generative adversarial networks. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1316–1324 (2018)
Yang, E., Deng, C., Liu, W., Liu, X., Tao, D., Gao, X.: Pairwise relationship guided deep hashing for cross-modal retrieval, pp. 1618–1625 (2017)
Zhang, Q., Lei, Z., Zhang, Z., Li, S.: Context-aware attention network for image-text retrieval. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3533–3542 (2020)
Zhen, L., Hu, P., Wang, X., Peng, D.: Deep supervised cross-modal retrieval. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10386–10395 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Jiang, Z., Lian, Z. (2023). Self-supervised Visual-Semantic Embedding Network Based on Local Label Optimization. In: Xu, Y., Yan, H., Teng, H., Cai, J., Li, J. (eds) Machine Learning for Cyber Security. ML4CS 2022. Lecture Notes in Computer Science, vol 13657. Springer, Cham. https://doi.org/10.1007/978-3-031-20102-8_31
Download citation
DOI: https://doi.org/10.1007/978-3-031-20102-8_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20101-1
Online ISBN: 978-3-031-20102-8
eBook Packages: Computer ScienceComputer Science (R0)