SELF-SUPERVISED SEQUENTIAL VARIATIONAL AUTOENCODER FOR DISENTANGLED DATA GENERATION

    公开(公告)号:WO2021096739A1

    公开(公告)日:2021-05-20

    申请号:PCT/US2020/058857

    申请日:2020-11-04

    Abstract: A computer-implemented method is provided for disentangled data generation. The method includes accessing (410), by a variational autoencoder, a plurality of supervision signals. The method further includes accessing (420), by the variational autoencoder, a plurality of auxiliary tasks that utilize the supervision signals as reward signals to learn a disentangled representation. The method also includes training (430) the variational autoencoder to disentangle a sequential data input into a time-invariant factor and a time- varying factor using a self-supervised training approach which is based on outputs of the auxiliary tasks obtained by using the supervision signals to accomplish the plurality of auxiliary tasks.

Patent Agency Ranking