Transfer Learning（迁移学习）

最新推荐文章于 2024-02-28 16:47:24 发布

原创

最新推荐文章于 2024-02-28 16:47:24 发布 · 1.3k 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#Deep Learning

本文介绍了迁移学习在深度学习中的应用场景，包括固定特征提取、微调ConvNet以及预训练模型的使用。通常，从ImageNet等大型数据集预训练的ConvNet可以作为固定特征提取器或进行微调，以适应新的任务。根据新数据集的大小和与原始数据集的相似性，选择合适的迁移学习策略，如仅训练线性分类器或全网微调。

Transfer Learning

In practice, very few people train an entire Convolutional Network from scratch (with random initialization), because it is relatively rare to have a dataset of sufficient size. Instead, it is common to pretrain a ConvNet on a very large dataset (e.g. ImageNet, which contains 1.2 million images with 1000 categories), and then use the ConvNet either as an initialization or a fixed feature extractor for the task of interest. The three major Transfer Learning scenarios look as follows:

ConvNet as fixed feature extractor. Take a ConvNet pretrained on ImageNet, remove the last fully-connected layer (this layer’s outputs are the 1000 class scores for a different task like ImageNet), then treat the rest of the ConvNet as a fixed feature extractor for the new dataset. In an AlexNet, this would compute a 4096-D vector for every image that contains the activations of the hidden layer immediately before the classifier. We call these featuresCNN codes. It is important for performance that these codes are ReLUd (i.e. thresholded at zero) if they were also thresholded during the