Transfer learning (TL) from pretrained deep models is a standard practice in modern medical image classification (MIC). However, what levels of features to be reused are problem-dependent, and uniformly finetuning all layers of pretrained models may be suboptimal. This insight has partly motivated the recent differential TL strategies, such as TransFusion (TF) and layer-wise finetuning (LWFT), which treat the layers in the pretrained models differentially. In this paper, we add one more strategy into this family, called TruncatedTL, which reuses and finetunes appropriate bottom layers and directly discards the remaining layers. This yields not only superior MIC performance but also compact models for efficient inference, compared to other differential TL methods. Our code is available at: https://github.com/sun-umn/TTL

翻译：从预训练深度模型中进行迁移学习（TL）是现代医学图像分类（MIC）中的标准做法。然而，应复用哪些层次的特征取决于具体问题，对所有预训练模型层进行统一微调可能并非最优。这一见解部分推动了近期差异化迁移学习策略的发展，如TransFusion（TF）和逐层微调（LWFT），这些策略对预训练模型中的各层进行差异化处理。本文在该策略家族中新增了一种方法，称为TruncatedTL，该方法复用并微调合适的底层，同时直接丢弃其余层。与其他差异化迁移学习方法相比，该方法不仅实现了更优的医学图像分类性能，而且能够获得紧凑模型以实现高效推理。我们的代码可在以下网址获取：https://github.com/sun-umn/TTL