Training Networks in Null Space of Feature Covariance With Self-Supervision for Incremental Learning
Abstract: In the context of incremental learning, a network is sequentially trained on a stream of tasks, where data from previous tasks are particularly assumed to be inaccessible. The major ...
Abstract: Using the underwater acoustic ranging information between master–slave autonomous underwater vehicles (AUVs), the error correction and cooperative ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback