- 专利标题: Soft label generation for knowledge distillation
-
申请号: US15860097申请日: 2018-01-02
-
公开(公告)号: US11410029B2公开(公告)日: 2022-08-09
- 发明人: Takashi Fukuda , Samuel Thomas , Bhuvana Ramabhadran
- 申请人: INTERNATIONAL BUSINESS MACHINES CORPORATION
- 申请人地址: US NY Armonk
- 专利权人: INTERNATIONAL BUSINESS MACHINES CORPORATION
- 当前专利权人: INTERNATIONAL BUSINESS MACHINES CORPORATION
- 当前专利权人地址: US NY Armonk
- 代理机构: Tutunjian & Bitetto, P.C, Randall Bluestone
- 主分类号: G06N3/08
- IPC分类号: G06N3/08
摘要:
A technique for generating soft labels for training is disclosed. A teacher model having a teacher side class set is prepared. A collection of class pairs for respective data units is obtained. Class pairs includes classes labelled to corresponding data units from the teacher side class set and a student side class set different from the teacher side class set. A training input is fed into the teacher model to obtain a set of outputs for the teacher side class set. A set of soft labels for the student side class set is calculated from the set of the outputs by using at least an output obtained for a class within a subset of the teacher side class set having relevance to the member of the student side class set, based at least in part on observations in the collection of the class pairs.
公开/授权文献
- US20190205748A1 SOFT LABEL GENERATION FOR KNOWLEDGE DISTILLATION 公开/授权日:2019-07-04
信息查询