TL;DR提出了一种名为 Deep Adaptation Networks 的方法,通过在现有神经网络中添加线性组合的新滤波器来实现学习新技能,而不影响已经学习的性能,以及在各种图像分类任务中表现出良好的效果。
Abstract
Given an existing trained neural network, it is often desirable to learn new
capabilities without hindering performance of those already learned. Existing
approaches either learn sub-optimal solutions, require jo