Xavier Suau, Federico Danieli, Thomas Anderson Keller, Arno Blaas, Chen Huang, Jason Ramapuram, Dan Busbridge, L. Zappella
{"title":"二维结构和近似等变表示","authors":"Xavier Suau, Federico Danieli, Thomas Anderson Keller, Arno Blaas, Chen Huang, Jason Ramapuram, Dan Busbridge, L. Zappella","doi":"10.48550/arXiv.2306.16058","DOIUrl":null,"url":null,"abstract":"Multiview Self-Supervised Learning (MSSL) is based on learning invariances with respect to a set of input transformations. However, invariance partially or totally removes transformation-related information from the representations, which might harm performance for specific downstream tasks that require such information. We propose 2D strUctured and EquivarianT representations (coined DUET), which are 2d representations organized in a matrix structure, and equivariant with respect to transformations acting on the input data. DUET representations maintain information about an input transformation, while remaining semantically expressive. Compared to SimCLR (Chen et al., 2020) (unstructured and invariant) and ESSL (Dangovski et al., 2022) (unstructured and equivariant), the structured and equivariant nature of DUET representations enables controlled generation with lower reconstruction error, while controllability is not possible with SimCLR or ESSL. DUET also achieves higher accuracy for several discriminative tasks, and improves transfer learning.","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"21 1","pages":"32749-32769"},"PeriodicalIF":0.0000,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"DUET: 2D Structured and Approximately Equivariant Representations\",\"authors\":\"Xavier Suau, Federico Danieli, Thomas Anderson Keller, Arno Blaas, Chen Huang, Jason Ramapuram, Dan Busbridge, L. Zappella\",\"doi\":\"10.48550/arXiv.2306.16058\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Multiview Self-Supervised Learning (MSSL) is based on learning invariances with respect to a set of input transformations. However, invariance partially or totally removes transformation-related information from the representations, which might harm performance for specific downstream tasks that require such information. We propose 2D strUctured and EquivarianT representations (coined DUET), which are 2d representations organized in a matrix structure, and equivariant with respect to transformations acting on the input data. DUET representations maintain information about an input transformation, while remaining semantically expressive. Compared to SimCLR (Chen et al., 2020) (unstructured and invariant) and ESSL (Dangovski et al., 2022) (unstructured and equivariant), the structured and equivariant nature of DUET representations enables controlled generation with lower reconstruction error, while controllability is not possible with SimCLR or ESSL. DUET also achieves higher accuracy for several discriminative tasks, and improves transfer learning.\",\"PeriodicalId\":74529,\"journal\":{\"name\":\"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning\",\"volume\":\"21 1\",\"pages\":\"32749-32769\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-06-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2306.16058\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2306.16058","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
摘要
多视图自监督学习(MSSL)是基于一组输入变换的不变性学习。然而,不变性从表示中部分或全部地删除了与转换相关的信息,这可能会损害需要此类信息的特定下游任务的性能。我们提出了二维结构化和等变表示(DUET),这是在矩阵结构中组织的二维表示,并且在作用于输入数据的转换方面是等变的。DUET表示维护关于输入转换的信息,同时保持语义表达。与SimCLR (Chen et al., 2020)(非结构化和不变)和ESSL (Dangovski et al., 2022)(非结构化和等变)相比,DUET表示的结构化和等变性质使其能够以较低的重构误差控制生成,而SimCLR或ESSL则不可能实现可控制性。DUET在一些判别性任务上也达到了更高的准确率,并改善了迁移学习。
DUET: 2D Structured and Approximately Equivariant Representations
Multiview Self-Supervised Learning (MSSL) is based on learning invariances with respect to a set of input transformations. However, invariance partially or totally removes transformation-related information from the representations, which might harm performance for specific downstream tasks that require such information. We propose 2D strUctured and EquivarianT representations (coined DUET), which are 2d representations organized in a matrix structure, and equivariant with respect to transformations acting on the input data. DUET representations maintain information about an input transformation, while remaining semantically expressive. Compared to SimCLR (Chen et al., 2020) (unstructured and invariant) and ESSL (Dangovski et al., 2022) (unstructured and equivariant), the structured and equivariant nature of DUET representations enables controlled generation with lower reconstruction error, while controllability is not possible with SimCLR or ESSL. DUET also achieves higher accuracy for several discriminative tasks, and improves transfer learning.