Gradients as Features for Deep Representation Learning

Understand

We address the challenging problem of deep representation learning--the efficient adaption of a pre-trained deep network to different tasks.

• Specifically, we propose to explore gradient-based features.
• These features are gradients of the model parameters with respect to a task-specific loss given an input sample.
• Our key innovation is the design of a linear model that incorporates both gradient and activation of the pre-trained network.