Gated Transfer Network for Transfer Learning

10/30/2018
by   Yi Zhu, et al.
0

Deep neural networks have led to a series of breakthroughs in computer vision given sufficient annotated training datasets. For novel tasks with limited labeled data, the prevalent approach is to transfer the knowledge learned in the pre-trained models to the new tasks by fine-tuning. Classic model fine-tuning utilizes the fact that well trained neural networks appear to learn cross domain features. These features are treated equally during transfer learning. In this paper, we explore the impact of feature selection in model fine-tuning by introducing a transfer module, which assigns weights to features extracted from pre-trained models. The proposed transfer module proves the importance of feature selection for transferring models from source to target domains. It is shown to significantly improve upon fine-tuning results with only marginal extra computational cost. We also incorporate an auxiliary classifier as an extra regularizer to avoid over-fitting. Finally, we build a Gated Transfer Network (GTN) based on our transfer module and achieve state-of-the-art results on six different tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/16/2020

Towards Accurate Knowledge Transfer via Target-awareness Representation Disentanglement

Fine-tuning deep neural networks pre-trained on large scale datasets is ...
research
05/27/2016

SNN: Stacked Neural Networks

It has been proven that transfer learning provides an easy way to achiev...
research
11/27/2019

Transfer Learning in Visual and Relational Reasoning

Transfer learning is becoming the de facto solution for vision and text ...
research
04/28/2022

Model Selection, Adaptation, and Combination for Deep Transfer Learning through Neural Networks in Renewable Energies

There is recent interest in using model hubs, a collection of pre-traine...
research
11/08/2022

When How to Transfer with Transfer Learning

In deep learning, transfer learning (TL) has become the de facto approac...
research
07/14/2020

Adversarially-Trained Deep Nets Transfer Better

Transfer learning has emerged as a powerful methodology for adapting pre...
research
07/04/2018

Transfer Learning for Clinical Time Series Analysis using Recurrent Neural Networks

Deep neural networks have shown promising results for various clinical p...

Please sign up or login with your details

Forgot password? Click here to reset