Abstract
Zero-shot learning (ZSL) refer to recognizing the new class without training samples. Traditionally, the projection function learned from visual features to semantic features is used for object recognition. However, few works will focus on accurate feature representation of recognition objects. The human designed semantics are not discriminative and sufficient to recognize different and new classes. In this paper, we propose to use the image reconstruction to extract enhanced semantics (ES) on salient region of image. The salient region of image is encoded corresponding to predefined attributes and ES features. And then decoded to original image of salient region. The Lifted structure feature embedding (LSFE) is applied to make the extended features more discriminative. Softmax is used for classification thus makes ES features more accurate. Experiments on two benchmark datasets AwA2 and CUB, demonstrate the effectiveness of the proposed approach.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sung, F., Yang, Y., Zhang, L., et al.: Learning to compare: relation network for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1199–1208 (2018)
Song, J, Shen, C, Yang, Y, et al.: Transductive unbiased embedding for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1024–1033 (2018)
Yu, Y., Ji, Z., Li, X., et al.: Transductive zero-shot learning with a self-training dictionary approach. IEEE Trans. Cybern. 48(10), 2908–2919 (2018)
He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 951–958 (2009)
Itti, L., Koch, C., Niebur, E.: A model of saliencybased visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254–1259 (1998)
Akata, Z., Perronnin, F., Harchaoui, Z., et al.: Label-embedding for attribute-based classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 819–826 (2013)
Rohrbach, M., Stark, M., Schiele, B.: Evaluating knowledge transfer and zero-shot learning in a large-scale setting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1641–1648 (2011)
Lampert, C.H., Nickisch, H., Harmeling, S.: Attribute-based classification for zero-shot visual object categorization. IEEE Trans. Pattern Anal. Mach. Intell. 36(3), 453–465 (2013)
Fu, J., Zheng, H., Mei, T.: Look closer to see better: recurrent attention convolutional neural network for fine-grained image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4438–4446 (2017)
Changpinyo, S., Chao, W.L., Gong, B., et al.: Synthesized classifiers for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5327–5336 (2016)
Oh Song, H., Xiang, Y., Jegelka, S., et al.: Deep metric learning via lifted structured feature embedding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4004–4012 (2016)
Hou, Q., Cheng, M.M., Hu, X., et al.: Deeply supervised salient object detection with short connections. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3203–3212 (2017)
Elhoseiny, M., Saleh, B., Elgammal, A.: Write a classifier: Zero-shot learning using purely textual descriptions. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2584–2591 (2013)
Frome, A., et al.: Devise: Adeepvisual-semantic embedding model. In: Proceedings of Advances in Neural Information Processing Systems, pp. 2121–2129 (2013)
Lei Ba, J., Swersky, K., Fidler, S.: Predicting deep zero-shot convolutional neural networks using textual descriptions. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4247–4255 (2015)
Xian, Y., Lampert, C.H., Schiele, B., et al.: Zero-shot learning—a comprehensive evaluation of the good, the bad and the ugly. IEEE Trans. Pattern Anal. Mach. Intell. 41(9), 2251–2265 (2018)
Wah, C., Branson, S.., Perona, P., et al.: Multiclass recognition and part localization with humans in the loop. In: International Conference on Computer Vision, pp. 2524–2531. IEEE (2011)
Russakovsky, O., Deng, J., Su, H., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)
Romera-Paredes, B., Torr, P.: An embarrassingly simple approach to zero-shot learning. In: International Conference on Machine Learning, pp. 2152–2161 (2015)
Li, Y., Zhang, J., Zhang, J., et al.: Discriminative learning of latent features for zero-shot recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7463–7471 (2018)
Norouzi, M., et al.: Zero-shot learning by convex combination of semantic embeddings. arXiv preprint arXiv:1312.5650 (2013)
Chao, W.-L., Changpinyo, S., Gong, B., Sha, F.: An empirical study and analysis of generalized zero-shot learning for object recognition in the wild. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 52–68. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_4
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Kodirov, E., Xiang, T., Fu, Z., et al.: Unsupervised domain adaptation for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision, pp. 2452–2460 (2015)
Kodirov, E., Xiang, T., Gong, S.: Semantic autoencoder for zero-shot learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3174–3183 (2017)
Ye, M., Guo, Y.: Zero-shot classification with discriminative semantic representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7140–7148 (2017)
Jiang, H., Wang, R., Shan, S., et al.: Learning discriminative latent attributes for zero-shot classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4223–4232 (2017)
Zhang, L., Xiang, T., Gong, S.: Learning a deep embedding model for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2021–2030 (2017)
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
Pan, Z., Zhu, A. (2020). Zero-Shot Learning Based on Salient Region and Enhanced Semantics. In: Peng, Y., et al. Pattern Recognition and Computer Vision. PRCV 2020. Lecture Notes in Computer Science(), vol 12306. Springer, Cham. https://doi.org/10.1007/978-3-030-60639-8_32
Download citation
DOI: https://doi.org/10.1007/978-3-030-60639-8_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60638-1
Online ISBN: 978-3-030-60639-8
eBook Packages: Computer ScienceComputer Science (R0)