ZS3D-Net: Zero-Shot Classification Network for 3D Models

被引：0
|
作者：
Bai J. [1 ,2 ]
Yuan T. [1 ]
Fan Y. [1 ]
机构：
[1] School of Computer Science and Engineering, North Minzu University, Yinchuan
[2] Key Laboratory of Images, Graphics Intelligent Processing of State Ethnic Affairs Commission, North Minzu University, Yinchuan
来源：
Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics | 2022年 / 34卷 / 07期
关键词：
3D model classification; deep learning; semantic manifold embedding; zero-shot learning;
D O I：
10.3724/SP.J.1089.2022.19173
中图分类号：
学科分类号：
摘要：
Zero-shot 3D model classification is very important for the understanding and analysis of 3D models. Aiming at the problems of lack of corresponding datasets and low accuracy of zero-shot 3D model classification, a 3D model dataset ZS3D is constructed and a deep learning network ZS3D-Net is proposed. The dataset consists of 41 classes, 1677 non-rigid 3D models with complete attributes of all classes, which can be regarded as the benchmark for zero-shot 3D model classification task. For the network, firstly, the visual features of the 3D models are effectively extracted through an ensemble learning sub-network. Then, the correlation between the visual features and semantic features of the unseen and seen classes can be constructed by a semantic manifold embedding sub-network. Finally, the unseen classes can be recognized based on above two sub-networks. On a traditional 3D model dataset and the proposed ZS3D, ZS3D-Net achieves 30.0% and 58.6% classification accuracy respectively, which are on par or better than the state-of-the-art methods. The experiments also demonstrate that the proposed method has good feasibility and validity. © 2022 Institute of Computing Technology. All rights reserved.
引用
收藏
页码：1118 / 1126
页数：8
相关论文
共 28 条
  • [1] Frome A, Corrado G S, Shlens J, Et al., DeViSE: a deep visual-semantic embedding model, Proceedings of Advances in Neural Information Processing Systems, pp. 2121-2129, (2013)
  • [2] Kodirov E, Xiang T, Gong S G., Semantic autoencoder for zero-shot learning, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4447-4456, (2017)
  • [3] Xian Y Q, Lorenz T, Schiele B, Et al., Feature generating networks for zero-shot learning, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5542-5551, (2018)
  • [4] Fu Y W, Hospedales T M, Xiang T, Et al., Transductive multi-view zero-shot learning, IEEE Transactions on Pattern Analysis and Machine Intelligence, 37, 11, pp. 2332-2345, (2015)
  • [5] Cheraghian A, Rahman S, Petersson L., Zero-shot learning of 3D point cloud objects, Proceedings of the 16th International Conference on Machine Vision Applications, pp. 1-6, (2019)
  • [6] Cheraghian A, Rahman S, Petersson L., Mitigating the hubness problem for zero-shot learning of 3D objects
  • [7] Cheraghian A, Rahman S, Campbell D, Et al., Transductive zero-shot learning for 3D point cloud classification, Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 912-922, (2020)
  • [8] Lampert C H, Nickisch H, Harmeling S., Learning to detect unseen object classes by between-class attribute transfer, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 951-958, (2009)
  • [9] Goodfellow I J, Pouget-Abadie J, Mirza M, Et al., Generative adversarial nets, Proceedings of Advances in Neural Information Processing Systems, pp. 2672-2680, (2014)
  • [10] Sariyildiz M B, Cinbis R G., Gradient matching generative networks for zero-shot learning, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2163-2173, (2019)
123