PredNet与预测编码:综述

Roshan Prakash Rane, Edit Szugyi, V. Saxena, André Ofner, S. Stober
{"title":"PredNet与预测编码:综述","authors":"Roshan Prakash Rane, Edit Szugyi, V. Saxena, André Ofner, S. Stober","doi":"10.1145/3372278.3390694","DOIUrl":null,"url":null,"abstract":"PredNet, a deep predictive coding network developed by Lotter et al., combines a biologically inspired architecture based on the propagation of prediction error with self-supervised representation learning in video. While the architecture has drawn a lot of attention and various extensions of the model exist, there is a lack of a critical analysis. We fill in the gap by evaluating PredNet both as an implementation of the predictive coding theory and as a self-supervised video prediction model using a challenging video action classification dataset. We design an extended model to test if conditioning future frame predictions on the action class of the video improves the model performance. We show that PredNet does not yet completely follow the principles of predictive coding. The proposed top-down conditioning leads to a performance gain on synthetic data, but does not scale up to the more complex real-world action classification dataset. Our analysis is aimed at guiding future research on similar architectures based on the predictive coding theory.","PeriodicalId":158014,"journal":{"name":"Proceedings of the 2020 International Conference on Multimedia Retrieval","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":"{\"title\":\"PredNet and Predictive Coding: A Critical Review\",\"authors\":\"Roshan Prakash Rane, Edit Szugyi, V. Saxena, André Ofner, S. Stober\",\"doi\":\"10.1145/3372278.3390694\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"PredNet, a deep predictive coding network developed by Lotter et al., combines a biologically inspired architecture based on the propagation of prediction error with self-supervised representation learning in video. While the architecture has drawn a lot of attention and various extensions of the model exist, there is a lack of a critical analysis. We fill in the gap by evaluating PredNet both as an implementation of the predictive coding theory and as a self-supervised video prediction model using a challenging video action classification dataset. We design an extended model to test if conditioning future frame predictions on the action class of the video improves the model performance. We show that PredNet does not yet completely follow the principles of predictive coding. The proposed top-down conditioning leads to a performance gain on synthetic data, but does not scale up to the more complex real-world action classification dataset. Our analysis is aimed at guiding future research on similar architectures based on the predictive coding theory.\",\"PeriodicalId\":158014,\"journal\":{\"name\":\"Proceedings of the 2020 International Conference on Multimedia Retrieval\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-02-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"10\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 2020 International Conference on Multimedia Retrieval\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3372278.3390694\",\"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 2020 International Conference on Multimedia Retrieval","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3372278.3390694","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 10

摘要

PredNet是由Lotter等人开发的一种深度预测编码网络,它将基于预测误差传播的生物学启发架构与视频中的自监督表示学习相结合。虽然体系结构吸引了大量的关注,并且存在着模型的各种扩展,但缺乏批判性的分析。我们通过评估PredNet作为预测编码理论的实现和使用具有挑战性的视频动作分类数据集的自监督视频预测模型来填补空白。我们设计了一个扩展模型来测试在视频的动作类别上调节未来帧预测是否能提高模型的性能。我们表明PredNet还没有完全遵循预测编码的原则。所提出的自顶向下的条件反射可以在合成数据上获得性能提升,但不能扩展到更复杂的现实世界动作分类数据集。我们的分析旨在指导未来基于预测编码理论的类似架构的研究。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
PredNet and Predictive Coding: A Critical Review
PredNet, a deep predictive coding network developed by Lotter et al., combines a biologically inspired architecture based on the propagation of prediction error with self-supervised representation learning in video. While the architecture has drawn a lot of attention and various extensions of the model exist, there is a lack of a critical analysis. We fill in the gap by evaluating PredNet both as an implementation of the predictive coding theory and as a self-supervised video prediction model using a challenging video action classification dataset. We design an extended model to test if conditioning future frame predictions on the action class of the video improves the model performance. We show that PredNet does not yet completely follow the principles of predictive coding. The proposed top-down conditioning leads to a performance gain on synthetic data, but does not scale up to the more complex real-world action classification dataset. Our analysis is aimed at guiding future research on similar architectures based on the predictive coding theory.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信