Multi-source pseudo-label learning of semantic segmentation for the scene recognition of agricultural mobile robots

References

• Matsuzaki S, Masuzawa H, Miura J. 3D semantic mapping in greenhouses for agricultural mobile robots with robust object recognition using robots' trajectory. In: IEEE International Conference on Systems, Man, and Cybernetics. Miyazaki: IEEE; 2018. p. 357–362.
   Google Scholar
• Matsuzaki S, Masuzawa H, Miura J. Image-based scene recognition for robot navigation considering traversable plants and its manual annotation-free training. IEEE Access. 2022;10:5115–5128.
   Web of Science ®Google Scholar
• Csurka G. Domain adaptation in computer vision applications. Cham: Springer International Publishing; 2017. (Advances in Computer Vision and Pattern Recognition).
   Google Scholar
• Richter SR, Vineet V, Roth S, et al. Playing for data: ground truth from computer games. In: European Conference on Computer Vision. Amsterdam: Springer; 2016. p. 102–118.
   Google Scholar
• Ros G, Sellart L, Materzynska J, et al. The SYNTHIA dataset: a large collection of synthetic images for semantic segmentation of Urban scenes. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition. Las Vegas, NV: IEEE; 2016. p. 3234–3243.
   Google Scholar
• Cordts M, Omran M, Ramos S, et al. The cityscapes dataset for semantic Urban scene understanding. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition. Las Vegas, NV: IEEE; 2016. p. 3213–3223.
   Google Scholar
• Zheng Z, Yang Y. Rectifying pseudo label learning via uncertainty estimation for domain adaptive semantic segmentation. Int J Comput Vis. 2020;129:1106–1120.
   Web of Science ®Google Scholar
• Zhang P, Zhang B, Zhang T, et al. Prototypical pseudo label denoising and target structure learning for domain adaptive semantic segmentation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, TN: IEEE; 2021. p. 12414–12424.
   Google Scholar
• Long J, Shelhamer E, Darrell T, et al. Fully convolutional networks for semantic segmentation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition. Bostan, MA: IEEE; 2015. p. 3431–3440.
   Google Scholar
• Badrinarayanan V, Kendall A, Cipolla R. SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell. 2017;39(12):2481–2495.
   PubMed Web of Science ®Google Scholar
• Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. Med Image Comput Comput Assist Interv. 2015;9351:234–241.
   Google Scholar
• He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition. Las Vegas, NV: IEEE; 2016. p. 770–778.
   Google Scholar
• Zhao H, Shi J, Qi X, et al. Pyramid scene parsing network. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition. Honolulu, HI: IEEE; 2017. p. 6230–6239.
   Google Scholar
• Chen Y, Li W, Chen X, et al. Learning semantic segmentation from synthetic data: a geometrically guided input-output adaptation approach. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA: IEEE; 2019. p. 1841–1850.
   Google Scholar
• Mehta S, Rastegari M, Caspi A, et al. ESPNet: efficient spatial pyramid of dilated convolutions for semantic segmentation. In: European Conference on Computer Vision. Munich: Springer; 2018. p. 561–580.
   Google Scholar
• Mehta S, Rastegari M, Shapiro L, et al. ESPNetv2: a light-weight, power efficient, and general purpose convolutional neural network. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA: IEEE; 2019. p. 9190–9200.
   Google Scholar
• Paszke A, Chaurasia A, Kim S, et al. ENet: a deep neural network architecture for real-time semantic segmentation. 2016. Tech Rep. 1606.02147v1. https://arxiv.org/pdf/1606.02147.pdf.
   Google Scholar
• Romera E, Alvarez JM, Bergasa LM, et al. ERFNet: efficient residual factorized convnet for real-time semantic segmentation. IEEE Trans Intell Transp Syst. 2018;19(1):263–272.
   Web of Science ®Google Scholar
• Lulio LC, Tronco ML, Porto AJ. JSEG-based image segmentation in computer vision for agricultural mobile robot navigation. In: IEEE International Symposium on Computational Intelligence in Robotics and Automation. Daejeon: IEEE; 2009. p. 240–245.
   Google Scholar
• Sharifi M, Chen X. A novel vision based row guidance approach for navigation of agricultural mobile robots in orchards. In: International Conference on Automation, Robotics and Applications. Queenstown: IEEE; 2015. p. 251–255.
   Google Scholar
• Aghi D, Cerrato S, Mazzia V, et al. Deep semantic segmentation at the edge for autonomous navigation in vineyard rows. 2021. Tech Rep. 2107.00700. http://arxiv.org/abs/2107.00700.
   Google Scholar
• Lin YK, Chen SF. Development of navigation system for tea field machine using semantic segmentation. IFAC-PapersOnLine. 2019;52(30):108–113.
   Google Scholar
• Yang B, Yan J, Lei Z, et al. Convolutional channel features. In: IEEE International Conference on Computer Vision. Santiago, Chile: IEEE; 2015. p. 82–90.
   Google Scholar
• Zhao S, Yue X, Zhang S, et al. A review of single-source deep unsupervised visual domain adaptation. 2020. Tech Rep. 2009.00155. http://arxiv.org/abs/2009.00155.
   Google Scholar
• Wilson G, Cook DJ. A survey of unsupervised deep domain adaptation. ACM Trans Intell Syst Technol. 2020; 11(5):1–46.
   PubMed Web of Science ®Google Scholar
• Hoffman J, Tzeng E, Park T, et al. CyCADA: cycle-consistent adversarial domain adaptation. In: International Conference on Machine Learning. Stockholm: PMLR; 2018. p. 1989–1998.
   Google Scholar
• Vu TH, Jain H, Bucher M, et al. ADVENT: adversarial entropy minimization for domain adaptation in semantic segmentation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA: IEEE; 2019. p. 2512–2521.
   Google Scholar
• Saito K, Ushiku Y, Harada T. Asymmetric tri-training for unsupervised domain adaptation. In: International Conference on Machine Learning. Sydney: PMLR; 2017. p. 2988–2997.
   Google Scholar
• Ganin Y, Ustinova E, Ajakan H, et al. Domain-adversarial training of neural networks. J Mach Learning Res. 2016;17(1):1–35.
   Google Scholar
• Tsai YH, Hung WC, Schulter S, et al. Learning to adapt structured output space for semantic segmentation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT: IEEE; 2018. p. 7472–7481.
   Google Scholar
• Biasetton M, Michieli U, Agresti G, et al. Unsupervised domain adaptation for semantic segmentation of Urban scenes. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Long Beach, CA; 2019. p. 1211–1220.
   Google Scholar
• Goodfellow IJ, Jean PA, Mirza M, et al. Generative adversarial nets. In: Conference on Neural Information Processing Systems. Montreal: Curran Associates, Inc.; 2014. p. 2672–2680.
   Google Scholar
• Zou Y, Yu Z, Vijaya Kumar BVK, et al. Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In: European Conference on Computer Vision. Munich: Springer; 2018. p. 289–305.
   Google Scholar
• Zou Y, Yu Z, Liu X, et al. Confidence regularized self-training. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA: IEEE; 2019. p. 5982–5991.
   Google Scholar
• Xu R, Chen Z, Zuo W, et al. Deep cocktail network: multi-source unsupervised domain adaptation with category shift. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT: IEEE; 2018. p. 3964–3973.
   Google Scholar
• Zhao S, Li B, Reed C, et al. Multi-source domain adaptation in the deep learning Era: a systematic survey. 2020. Tech Rep. 2002.12169. http://arxiv.org/abs/2002.12169.
   Google Scholar
• Zhao S, Li B, Yue X, et al. Multi-source domain adaptation for semantic segmentation. In: Conference on Neural Information Processing Systems. Vancouver: Curran Associates, Inc.; 2019. p. 7287–7300.
   Google Scholar
• Nigam I, Huang C, Ramanan D. Ensemble knowledge transfer for semantic segmentation. In: IEEE Winter Conference on Applications of Computer Vision. Lake Tahoe, NV: IEEE; 2018. p. 1499–1508.
   Google Scholar
• Brostow GJ, Fauqueur J, Cipolla R. Semantic object classes in video: a high-definition ground truth database. Pattern Recognit Lett. 2009;30(2):88–97.
   Web of Science ®Google Scholar
• Valada A, Oliveira GL, Brox T, et al. Deep multispectral semantic scene understanding of forested environments using multimodal fusion. In: International Symposium for Experimental Robotics. Tokyo: Springer; 2016. p. 465–477.
   Google Scholar
• Kingma DP, Lei Ba J. Adam: a method for stochastic optimization. In: International Conference on Learning Representations. San Diego, CA: ICLR; 2015.
   Google Scholar
• Zlateski A, Jaroensri R, Sharma P, et al. On the importance of label quality for semantic segmentation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT: IEEE; 2018. p. 1479–1487.
   Google Scholar
• Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: machine learning in python. J Mach Learn Res. 2011;12:2825–2830.
   Web of Science ®Google Scholar
• Felzenszwalb PF, Huttenlocher DP. Efficient graph-based image segmentation. Int J Comput Vis. 2004 Sep;59(2): 167–181.
   Web of Science ®Google Scholar
• Van der walt S, Schönberger JL, Nunez-Iglesias J, et al. Scikit-image: image processing in python. PeerJ. 2014;2014(1):1–18.
   Google Scholar
• Kim D, Oh SM, Rehg JM. Traversability classification for UGV navigation: a comparison of patch and superpixel representations. In: IEEE/RSJ International Conference on Intelligent Robots and Systems. San Diego, CA: IEEE; 2007. p. 3166–3173.
   Google Scholar
• Leung T, Malik J. Representing and recognizing the visual appearance of materials using three-dimensional textons. Int J Comput Vis. 2001;43(1):29–44.
   Web of Science ®Google Scholar
• Chen LC, Papandreou G, Kokkinos I, et al. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell. 2018;40(4):834–848.
   PubMed Web of Science ®Google Scholar
• Mishra P, Sarawadekar K. Polynomial learning rate policy with warm restart for deep neural network. In: IEEE Region 10 Conference. Kochi: IEEE; 2019. p. 2087–2092.
   Google Scholar
• Zheng Z, Yang Y. Unsupervised scene adaptation with memory regularization in vivo. In: International Joint Conference on Artificial Intelligence. Yokohama: International Joint Conferences on Artificial Intelligence Organization; 2020. p. 1076–1082.
   Google Scholar