Yuria Shimizu

Relational Knowledge Distillation Brings DNN Representations Close Enough to Humans to Be Aligned Without Supervision

Fine-tuning pre-trained DNNs with Relational Knowledge Distillation, an established relational transfer method, brings DNNs close enough to humans to be aligned at the individual-object level on this test set, and indicates that relational transfer from humans brings the global structure of pre-trained DNNs close enoug...