Learning from a Teacher using Unlabeled Data
This work addresses model compression and quality improvement for machine learning practitioners, but it appears incremental as it builds on existing knowledge distillation techniques.
The paper tackled the problem of knowledge transfer from a teacher model to a student model using unlabeled out-of-distribution data, showing promising results on MNIST, CIFAR-10, and Caltech-256 datasets.
Knowledge distillation is a widely used technique for model compression. We posit that the teacher model used in a distillation setup, captures relationships between classes, that extend beyond the original dataset. We empirically show that a teacher model can transfer this knowledge to a student model even on an {\it out-of-distribution} dataset. Using this approach, we show promising results on MNIST, CIFAR-10, and Caltech-256 datasets using unlabeled image data from different sources. Our results are encouraging and help shed further light from the perspective of understanding knowledge distillation and utilizing unlabeled data to improve model quality.