Learning from a Teacher using Unlabeled Data

2019/11/13 by Gaurav Menghani, Sujith Ravi, Menghani, Gaurav +1
Computer Science · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Machine Learning and Data Classification

paper · pdf · doi:10.48550/arxiv.1911.05275

openalex publication_date 2019/11/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• A Survey of Model Compression and Acceleration for Deep Neural Networks

Related

• What Makes a Good Dataset for Knowledge Distillation?
• Understanding and Improving Knowledge Distillation
• Knowledge Distillation Beyond Model Compression
• Improve Knowledge Distillation via Label Revision and Data Selection
• Residual Knowledge Distillation