用于零样本学习的语义自动编码器(An implementation of SAE in MATLAB)

上传者: 59771180 | 上传时间: 2023-03-31 21:13:36 | 文件大小: 13KB | 文件类型: ZIP
Existing zero-shot learning (ZSL) models typically learn a projection function from a visual feature space to a semantic embedding space (e.g.~attribute space). However, such a projection function is only concerned with predicting the training seen class semantic representation (e.g.~attribute prediction) or classification. When applied to test data, which in the context of ZSL contains different (unseen) classes without training data, a ZSL model typically suffers from the project domain shift

文件下载

资源详情

[{"title":"( 11 个子文件 13KB ) 用于零样本学习的语义自动编码器(An implementation of SAE in MATLAB)","children":[{"title":"SAE-master","children":[{"title":"data_zsl","children":[{"title":"README.md <span style='color:#111;'> 263B </span>","children":null,"spread":false}],"spread":true},{"title":"library","children":[{"title":"zsl_el.m <span style='color:#111;'> 716B </span>","children":null,"spread":false},{"title":"SAE.m <span style='color:#111;'> 344B </span>","children":null,"spread":false},{"title":"NormalizeRows.m <span style='color:#111;'> 1.67KB </span>","children":null,"spread":false},{"title":"label_matrix.m <span style='color:#111;'> 581B </span>","children":null,"spread":false},{"title":"NormalizeFea.m <span style='color:#111;'> 1.16KB </span>","children":null,"spread":false}],"spread":true},{"title":"cub_demo.m <span style='color:#111;'> 1.81KB </span>","children":null,"spread":false},{"title":"ImNet_2_demo.m <span style='color:#111;'> 2.20KB </span>","children":null,"spread":false},{"title":"awa_demo.m <span style='color:#111;'> 1.34KB </span>","children":null,"spread":false}],"spread":true},{"title":"SAE-master.zip <span style='color:#111;'> 7.16KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 2.06KB </span>","children":null,"spread":false}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明