Abstract
Current state-of-the-art semantic segmentation models achieve remarkable success in segmentation accuracy. However, the huge model size and computing cost restrict their applications on low-latency online systems or devices. Knowledge distillation has been one popular solution for compressing large-scale segmentation models, which train a small segmentation model from a large teacher model. However, one teacher model’s knowledge may be insufficiently diverse to train an accurate student model. Meanwhile, the student model may inherit bias from the teacher model. This paper proposes a multi-view knowledge distillation framework called MVKD for efficient semantic segmentation. MVKD could aggregate the multi-view knowledge from multiple teacher models and transfer the multi-view knowledge to the student model. In MVKD, we introduce one multi-view co-tuning strategy to acquire uniformity among the multi-view knowledge in features from different teachers. In addition, we propose a multi-view feature distillation loss and a multi-view output distillation loss to transfer the multi-view knowledge in the features and outputs from multiple teachers to the student. We evaluate the proposed MVKD on three benchmark datasets, Cityscapes, CamVid, and Pascal VOC 2012. Experimental results demonstrate the effectiveness of the proposed MVKD in compressing semantic segmentation models.
Similar content being viewed by others
References
Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 12, 2481–2495 (2017)
Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn. (2017)
Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., Schiele, B.: The cityscapes dataset for semantic urban scene understanding. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn., pp. 3213–3223 (2016)
Dvornik, N., Mairal, J., Schmid, C.: Diversity with cooperation: Ensemble methods for few-shot classification. In: Proc. IEEE Int. Conf. Comp. Vis., pp. 3722–3730. IEEE (2019). 10.1109/ICCV.2019.00382. https://doi.org/10.1109/ICCV.2019.00382
Everingham, M., Gool, L.V., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. Int. J. Comp. ViS. 88(2), 303–338 (2010). https://doi.org/10.1007/s11263-009-0275-4
Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., Lu, H.: Dual attention network for scene segmentation. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn., pp. 3146–3154 (2019)
Fukuda, T., Suzuki, M., Kurata, G., Thomas, S., Cui, J., Ramabhadran, B.: Efficient Knowledge Distillation from an Ensemble of Teachers. In: Interspeech, pp. 3697–3701. ISCA (2017). https://doi.org/10.21437/Interspeech.2017-614
He, T., Shen, C., Tian, Z., Gong, D., Sun, C., Yan, Y.: Knowledge adaptation for efficient semantic segmentation. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn., pp. 578–587 (2019)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv: Comp. Res. Repository abs/1503.02531 (2015). arxiv.org/abs/1503.02531
Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: Ccnet: Criss-cross attention for semantic segmentation. In: Proc. IEEE Int. Conf. Comp. Vis., pp. 603–612 (2019)
Jain, J., Singh, A., Orlov, N., Huang, Z., Li, J., Walton, S., Shi, H.: Semask: Semantically masked transformers for semantic segmentation. arXiv preprint arXiv:2112.12782 (2021)
Lin, G., Milan, A., Shen, C., Reid, I.: Refinenet: Multi-path refinement networks for high-resolution semantic segmentation. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn., pp. 5168–5177 (2017). https://doi.org/10.1109/CVPR.2017.549
Liu, Y., Chen, K., Liu, C., Qin, Z., Luo, Z., Wang, J.: Structured knowledge distillation for semantic segmentation. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn., pp. 2604–2613 (2019). https://doi.org/10.1109/CVPR.2019.00271
Park, S., Kwak, N.: Feature-level ensemble knowledge distillation for aggregating knowledge from multiple networks. In: Proceedings of the European Conference on Artificial Intelligence (ECAI), vol. 325, pp. 1411–1418. IOS Press (2020). 10.3233/FAIA200246. https://doi.org/10.3233/FAIA200246
Paszke, A., Chaurasia, A., Kim, S., Culurciello, E.: Enet: A deep neural network architecture for real-time semantic segmentation. arXiv: Comp. Res. Repository abs/1606.02147 (2016)
Sachin, M., Mohammad, R., Anat, C., Linda, S., Hannaneh, H.: Espnet: Efficient spatial pyramid of dilated convolutions for semantic segmentation. In: Proc. Eur. Conf. Comp. Vis., pp. 552–568 (2018)
Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 640–651 (2016)
Shen, Z., He, Z., Xue, X.: Meal: Multi-model ensemble via adversarial learning. In: Proc. AAAI Conf. Artificial Intell., pp. 4886–4893 (2019)
Shu, C., Liu, Y., Gao, J., Yan, Z., Shen, C.: Channel-wise knowledge distillation for dense prediction. In: Proc. IEEE Int. Conf. Comp. Vis., pp. 5311–5320 (2021)
Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn., pp. 5693–5703 (2019)
Tan, M., Le, Q.: Efficientnet: Rethinking model scaling for convolutional neural networks. In: Proc. Int. Conf. Mach. Learn., pp. 6105–6114. PMLR (2019)
Wang, C., Zhong, J., Dai, Q., Li, R., Yu, Q., Fang, B.: Local structure consistency and pixel-correlation distillation for compact semantic segmentation. Applied Intelligence, 53(6), 6307–6323 (2022)
Wang, Y., Zhou, W., Jiang, T., Bai, X., Xu, Y.: Intra-class feature variation distillation for semantic segmentation. In: Proc. Eur. Conf. Comp. Vis., pp. 346–362. Springer (2020)
Wu, C., Wu, F., Huang, Y.: One teacher is enough? pre-trained language model distillation from multiple teachers. In: Proc. Annual Meeting of the Association for Computational Linguistics (ACL), pp. 4408–4413 (2021). 10.18653/v1/2021.findings-acl.387. https://doi.org/10.18653/v1/2021.findings-acl.387
Wu, C., Wu, F., Qi, T., Huang, Y.: Unified and effective ensemble knowledge distillation. arXiv preprint arXiv:2204.00548 (2022)
Wu, M., Chiu, C., Wu, K.: Multi-teacher knowledge distillation for compressed video action recognition on deep neural networks. In: Pro. IEEE Conf. Acoustics, Speech and Signal Processing, pp. 2202–2206. IEEE (2019). 10.1109/ICASSP.2019.8682450. https://doi.org/10.1109/ICASSP.2019.8682450
Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: Simple and efficient design for semantic segmentation with transformers. In: Proc. Advances in Neural Inf. Process. Syst., pp. 12077–12090 (2021)
You, S., Xu, C., Xu, C., Tao, D.: Learning from multiple teacher networks. In: Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 1285–1294 (2017). 10.1145/3097983.3098135. https://doi.org/10.1145/3097983.3098135
Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: Bisenet: Bilateral segmentation network for real-time semantic segmentation. In: Proc. Eur. Conf. Comp. Vis., pp. 325–341 (2018)
Yuan, Y., Chen, X., Wang, J.: Object-contextual representations for semantic segmentation. In: Proc. Eur. Conf. Comp. Vis., pp. 173–190 (2020)
Yuan, Y., Wang, J.: Ocnet: Object context network for scene parsing. arXiv: Comp. Res. Repository abs/1809.00916 (2018). http://arxiv.org/abs/1809.00916
Zhang, X., Lu, S., Gong, H., Luo, Z., Liu, M.: Amln: adversarial-based mutual learning network for online knowledge distillation. In: Proc. Eur. Conf. Comp. Vis., pp. 158–173. Springer (2020)
Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn., pp. 4320–4328 (2018)
Zhao, H., Qi, X., Shen, X., Shi, J., Jia, J.: Icnet for real-time semantic segmentation on high-resolution images. In: Proc. Eur. Conf. Comp. Vis., pp. 405–420 (2018)
Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn., pp. 2881–2890 (2017). https://doi.org/10.1109/CVPR.2017.660
Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., Torr, P.H.: Conditional random fields as recurrent neural networks. In: Proc. IEEE Int. Conf. Comp. Vis., pp. 1529–1537 (2015)
Zheng, S., Lu, J., Zhao, H., Zhu, X., Luo, Z., Wang, Y., Fu, Y., Feng, J., Xiang, T., Torr, P.H.S., Zhang, L.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn., pp. 6881–6890 (2021). https://doi.org/10.1109/CVPR46437.2021.00681
Zhou, Z.H.: Ensemble learning. In: Machine learning, pp. 181–210. Springer (2021)
Acknowledgements
This work is partially supported by the National Natural Science Foundation of China (62176029 and 61876026), the National Key Research and Development Program of China (2017YFB1402401), the Key Research Program of Chongqing Science and Technology Bureau (cstc2020jscx-msxmX0149).
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
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wang, C., Zhong, J., Dai, Q. et al. Multi-view knowledge distillation for efficient semantic segmentation. J Real-Time Image Proc 20, 39 (2023). https://doi.org/10.1007/s11554-023-01296-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11554-023-01296-6