DeepAI AI Chat
Log In Sign Up

Beyond Fine Tuning: A Modular Approach to Learning on Small Data

by   Ark Anderson, et al.
Eastern Washington University

In this paper we present a technique to train neural network models on small amounts of data. Current methods for training neural networks on small amounts of rich data typically rely on strategies such as fine-tuning a pre-trained neural network or the use of domain-specific hand-engineered features. Here we take the approach of treating network layers, or entire networks, as modules and combine pre-trained modules with untrained modules, to learn the shift in distributions between data sets. The central impact of using a modular approach comes from adding new representations to a network, as opposed to replacing representations via fine-tuning. Using this technique, we are able surpass results using standard fine-tuning transfer learning approaches, and we are also able to significantly increase performance over such approaches when using smaller amounts of data.


page 5

page 6


Surgical Fine-Tuning Improves Adaptation to Distribution Shifts

A common approach to transfer learning under distribution shift is to fi...

Depth Augmented Networks with Optimal Fine-tuning

Convolutional neural networks (CNN) have been shown to achieve state-of-...

RADAM: Texture Recognition through Randomized Aggregated Encoding of Deep Activation Maps

Texture analysis is a classical yet challenging task in computer vision ...

Tuning Modular Networks with Weighted Losses for Hand-Eye Coordination

This paper introduces an end-to-end fine-tuning method to improve hand-e...

Feature Imitating Networks

In this paper, we introduce a novel approach to neural learning: the Fea...

Train and You'll Miss It: Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings

Our goal is to enable machine learning systems to be trained interactive...

Learning to Transfer Dynamic Models of Underactuated Soft Robotic Hands

Transfer learning is a popular approach to bypassing data limitations in...