This lecture introduces pretraining and fine-tuning for few-shot learning. This method is simple but comparable to the state-of-the-art. This lecture discusses 3 tricks for improving fine-tuning: (1) a good initialization, (2) entropy regularization, and (3) combine cosine similarity and softmax classifier.

Sides: [ Ссылка ]

Lectures on few-shot learning:
1. Basic concepts: [ Ссылка ]
2. Siamese networks: [ Ссылка ]
3. Pretraining and fine-tuning: [ Ссылка ]


Reference:
1. Chen, Liu, Kira, Wang, & Huang. A Closer Look at Few-shot Classification. In ICLR, 2019.
2. Dhillon, Chaudhari, Ravichandran, & Soatto. A baseline for few-shot image classification. In ICLR, 2020.
3. Chen, Wang, Liu, Xu, & Darrell. A New Meta-Baseline for Few-Shot Learning. arXiv, 2020.

свернуть