Abstract
In this paper, a novel model is proposed to segment image instance based on fractional-order chaotic synchronization network and reinforcement learning method. In the proposed model, fractional-order network is used for the preliminary image segmentation, which can obtain fine-grained information to provide a guiding strategy for the exploration of reinforcement learning; afterward, reinforcement learning method is committed to generate high-quality bounding contour curves for the object instances, which can combine the pixel features with local information in the image to improve the overall accuracy. Compared with other fractional-order models, the experimental results show that our proposed model achieves higher accuracy on the datasets of Pascal VOC2007 and Pascal VOC2012.
Similar content being viewed by others
References
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), IEEE, pp. 386–397 (2018)
Dai, J., He, K., Sun, J.: Instance-Aware Semantic Segmentation via Multi-task Network Cascades. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 3150–3158 (2016)
Hariharan, B., Arbeláez, P., Girshick, R., Malik, J.: Hypercolumns for object segmentation and fine-grained localization. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 447–456 (2015)
Long, J., Shelhamer, E., Darrell, T.: Fully Convolutional Networks for Semantic Segmentation. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), IEEE, pp. 640–651 (2015)
Chen, K., Wang, D.L.: A dynamically coupled neural oscillator network for image segmentation. Neural Netw. 15(3), 423–439 (2002)
Breve, F.A., Zhao, L., Quiles, M.G., et al.: Chaotic phase synchronization and desynchronization in an oscillator network for object selection. Neural Netw. 22(5–6), 728–737 (2009)
Zhao, L., Breve, F.A.: Chaotic synchronization in 2D lattice for scene segmentation. Neurocomputing 71(13–15), 2761–2771 (2008)
Larochelle, H., Hinton, G.E.: Learning to combine foveal glimpses with a third-order Boltzmann machine. In: Advances in Neural Information Processing Systems 23: Conference on Neural Information Processing Systems, pp. 1243–1251.
Li, Y.: Deep Reinforcement Learning: An Overview. arXiv preprint arXiv:1701.07274 (2017)
Saleem, A.B., Lien, A.D., Krumin, M., et al.: Subcortical source and modulation of the narrowband gamma oscillation in mouse visual cortex. Neuron 93(2), 315–322 (2017)
Luciano, L., Ben, H.A.: Deep similarity network fusion for 3D shape classification. Vis. Comput. 35(6–8), 1171–1180 (2019)
Quiles, M.G., Wang, D.L., Zhao, L., et al.: Selecting salient objects in real scenes: an oscillatory correlation model. Neural Netw. 24(1), 54–64 (2011)
Hungenahally, S.: Neural basis for the design of fractional-order perceptual filters: applications in image enhancement and coding. In: 1995 IEEE International Conference on Systems, Man and Cybernetics. Intelligent Systems for the 21st Century, IEEE, pp. 4626–4631 (1995)
Bai, J., Feng, X.: Fractional-order anisotropic diffusion for image denoising. In: IEEE Transactions on Image Processing, IEEE, pp. 2492–2502 (2007)
Wang, D.L., Terman, D.: Locally excitatory globally inhibitory oscillator networks. IEEE Trans. Neural Netw. 6(1), 283–286 (1995)
Zhao, L., Cupertino, T.H., Bertini, J.R.: Chaotic synchronization in general network topology for scene segmentation. Neurocomputing 71(16–18), 3360–3366 (2008)
Breve, F.A., Zhao, L., Quiles, M.G., Macau, E.E.N.: Chaotic phase synchronization and desynchronization in an oscillator network for object selection. Neural Netw. 22(5–6), 728–737 (2009)
Benicasa, A.X., Quiles, M.G., Silva, T.C., et al.: An object-based visual selection framework. Neurocomputing 180(5), 35–54 (2016)
Qiao, Y., Liu, X., Miao, J., et al.: A neural network model for visual selection and shifting. J. Integr. Neurosci. 15(3), 1–15 (2016)
Xiaoran, L., Shangbo, Z., Hongbin, T., et al.: A novel fractional-order chaotic phase synchronization model for visual selection and shifting. Entropy 20(4), 251 (2018)
Gondy, L.A., Thomas, C.R.B., Naïve, B.: Programs for machine learning. In: Advances in Neural Information Processing Systems (NIPS), Springer, pp. 937–944 (1993)
Mnih, V., et al.: Playing Atari with Deep Reinforcement Learning. arXiv preprint arXiv:1312.5602 (2013)
Lillicrap, T.P., Hunt, J.J., Pritzel, A., Heess, N., Erez, T., Tassa, Y, Silver, D., Wierstra, D.: Continuous control with deep reinforcement learning. arXiv preprint arXiv, arXiv:1509.02971 (2015)
Krull, A., Brachmann, E., Nowozin, S., et al.: Poseagent: Budget-constrained 6d object pose estimation via reinforcement learning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 2566–2574 (2017)
Caicedo, J.C., Lazebnik, S.: Active Object Localization with Deep Reinforcement Learning. In: 2015 IEEE International Conference on Computer Vision (ICCV), IEEE, pp. 2488–2496 (2015)
Kong, X., Xin, B., Wang, Y., Hua, G.: Collaborative Deep Reinforcement Learning for Joint Object Search. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7072–7081. IEEE (2017)
Han, J., Yang, L., Zhang, D., et al.: Reinforcement Cutting-Agent Learning for Video Object Segmentation. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 9080–9089 (2018)
Abbeel, P., Ng, A.Y.: Apprenticeship learning via inverse reinforcement learning. In: Proceedings of the 21st International Conference on Machine Learning (ICML), ACM, pp. 0–4 (2004)
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
About this article
Cite this article
Li, X., Wu, G., Zhou, S. et al. Active instance segmentation with fractional-order network and reinforcement learning. Vis Comput 38, 3027–3040 (2022). https://doi.org/10.1007/s00371-021-02174-7
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-021-02174-7