ABSTRACT
This paper proposes a multi-domain sample classification method based on Baidu API's general object recognition function. we used three datasets in the experiment,including CIFAR-10, CIFAR-100, and Mini-ImageNet. For an unknown sample belonging to these three datasets, we first predict which domain it may belong to by using the output results of Baidu API, and then obtain the label of the sample by training a model on that domain. Compared with existing methods, our method reduces the number of high-performance models that need to be trained and reduces the computational difficulty. Experimental results show that our method is more convenient and accurate.
- Zhangie Cao, Kaichao You, Mingsheng Long,Jianmin Wang, and Qiang Yang.2019. Learning to transfer examples for partial domain adaptation.IlnProceedings of the IEEE/CVF conference on computer vision and pattern recognition.2985-2994.Google Scholar
- ChenhuiChu and Rui Wang.2018.A survey of domain adaptation for neural machine translation. arXiv preprint arXiv1806.0258 (2018)Google Scholar
- Yaroslav Ganin, Evgeniya Ustinova,Hana Ajakan,Pascal Germain,Hugo Larochelle,Francois Laviolette,Maio Marchand, and Vietor Lempitsky. 2016. Domain-adversarial training of neural networks. The journal of machine learning research 17, 1 (2016),2096-2030.Google Scholar
- Jiang Guo, Darsh J Shah, and Regina Barzilay. 2018. Multi-source domain adaptation with mixture of experts.arAXiv preprint arXiv:1809.02256(2018)Google Scholar
- Zhengyu He. 2020. Deep learning in image classification: A survey report.In 2020 2nd International Conference on nformation Technology and Computer Application (ITCA). IEEE, 174-177.Google Scholar
- Ignacio Hounie, Luiz FO Chamon,and Alejandro Ribeiro.20.22.Automatic Data Augmentation via lnvariance-Constrained Learning. arXiv preprintarXiv:2209.15031(2022).Google Scholar
- Shell Xu Hu, Da Li. Jan Sthmer,Minyoung Kim, and Timothy M Hospedales.2022. Pushing the limits of simple pipelines for few-shot learning;External data and fine-tuning make a dfference.In Procedings of the IEE/CVFConference on Computer Vision and Pattern Recognition .9068-9077.Google Scholar
- Gao Huang.Zhuang Lliu, L.aurens Van Der Maten, and Kilian Q Weinberger.2017. Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4700-4708.Google Scholar
- Jack Lanchantin,Tianlu Wang,Vicente Ordonez, and Yanjun Qi.2021.General muli-label image lassification with transformers ln Procedimgsof the IEEE/CVF Conference on Computer Vision and Pattern Recognition.16478-16488.Google Scholar
- Ze Liu,Yutong Lin, Yue Cao,Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo.2021. Swin transformer: Hierarchical visiontransformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision.10012-10022.Google Scholar
- Andrew Maas, Quoc V Le,Tyler M O'neil, Oriol Vinyals,Patrick Nguyen, and Andrew Y Ng. 2012.Recurrent neural networks for noise reduction inrobust ASR.(2012).Google Scholar
- Ishan Misra and Laurens van der Maaten. 2020. Self-supervised learning of pretext-invariant representations. in Proceings of the TEECVPcorference on computer vision and pattern recognition.6707-6717.Google Scholar
- Sinno Jialin Pan and Qiang Yang.2010.A survey on transfer learning. TEE Transactions on knowledge and data engineering 2,10(2010),1345-1359.Google Scholar
- Sainbayar Sukhbaatar,Joan Bruna, Manohar Paluri, Lubomir Bourdev, and Rob Fergus.2014. Training convolutional networks with noisy label.arXiv preprint arXiv:1406.2080(2014).Google Scholar
- Mingxing Tan and Quoc Le.2019.Eficientnet:Rethinking model scaling for convolutional neural networks. In International conference on machinelearning. PMLR,6105-6114.Google Scholar
- Onur Tasar,Yuliya Tarabalka, Alain Giros,Pierre Alliez, and Sebastien Clerc. 2020. StandardGAN: Multi-source domain adaptation for semanticsegmentation of very high resolution satellite images by data standardization.In Proceedings of the IE/CVFConference on Computer Vision andPattern Recognition Workshops. 192-193.Google Scholar
- Hugo Touvron,Matthieu Cord,Matthjs Douze, Francisco Massa,Alexandre Sablayrolles, and Herve Jlerou.2021.Training dats-eficient imagetransformers & distillation through attention. In International conference on machine learning.PMLR,10347-10357.Google Scholar
- Jingdong Wang,Ke Sun, Tianheng Cheng,Borui Jiang.Chaorui Deng.Yang Zhao, Dong Liu, Yladong Mut.MingkuiTan.XKinggang Wang 02.Deep high-resolution representation learning for visual recognition .IE transactions on patten analyis and machine intelience 43,10(2a2a0,3349-3364.Google Scholar
- Ruijia Xu, Ziliang Chen, Wangmeng Zuo,JunjieYan, and Liang Lin.2018. Deep cocktail network: Multi-source unsupervised domain adaptationwith category shift. In Proceedings of the IEEE conference on computer vision and pattern recognition.3964-3973.Google Scholar
- Sergey Zagoruyko and Nikos Komodakis. 2016. Wide residual networks. arXiv preprint arXiv:1605.07146(2016).Google Scholar
- Fuzhen Zhuang,Zhiyuan Qi,Keyu Duan,Dongbo Xi, Yongchun Zhu,Hengshu Zhu, Hui Xiong, and Qing He. 2020.A comprehensive survey ontransfer learning. Proc.IEEE 109,1(2020),43-76.Google ScholarCross Ref
Index Terms
- Research on Multi-Domain Sample Classification Method Based on Baidu API
Recommendations
Selected Sample Retraining Semi-supervised Learning Method for Aerial Scene Classification
Artificial IntelligenceAbstractThe performance of scene classification for remote sensing images based on deep neural networks is limited by the number of labeled data. To alleviate this problem, a variety of methods have been proposed to apply semi-supervised learning to ...
Collaborative Multi-domain Sentiment Classification
ICDM '15: Proceedings of the 2015 IEEE International Conference on Data Mining (ICDM)Sentiment classification is a hot research topic in both industrial and academic fields. The mainstream sentiment classification methods are based on machine learning and treat sentiment classification as a text classification problem. However, ...
DaCon: Multi-Domain Text Classification Using Domain Adversarial Contrastive Learning
Artificial Neural Networks and Machine Learning – ICANN 2023AbstractMulti-Domain Text Classification (MDTC) aims to classify text from a specific domain based on knowledge learned from multiple other domains. Recent state-of-the-art approaches address the MDTC problem using a shared-private model design (i.e., a ...
Comments