Back to questions

Self-supervised pretraining на unlabeled sequences

Есть много неразмеченных driving/log sequences и мало labels для редких событий. Какие self-supervised подходы можно использовать до supervised fine-tuning?

Answer as you would in an interview

Answer aloud or write down a few key points. The text field is optional; the review opens after your attempt.

Loading
Self-supervised pretraining на unlabeled sequences — interview question — ML Mentor