Unsupervised Network Pretraining via Encoding Human Design

TL;DR

This paper introduces a novel unsupervised pretraining method for deep neural networks in computer vision by teaching them to replicate hand-designed feature extraction processes, leading to improved classification performance.

Contribution

It presents a new pretraining approach that incorporates human-designed feature extraction processes into neural network training, enhancing visual object recognition.

Findings

Pretraining via feature replication improves classification accuracy.

Replicating HOG and region covariance features enhances model performance.

Method outperforms baseline approaches after finetuning.

Abstract

Over the years, computer vision researchers have spent an immense amount of effort on designing image features for the visual object recognition task. We propose to incorporate this valuable experience to guide the task of training deep neural networks. Our idea is to pretrain the network through the task of replicating the process of hand-designed feature extraction. By learning to replicate the process, the neural network integrates previous research knowledge and learns to model visual objects in a way similar to the hand-designed features. In the succeeding finetuning step, it further learns object-specific representations from labeled data and this boosts its classification power. We pretrain two convolutional neural networks where one replicates the process of histogram of oriented gradients feature extraction, and the other replicates the process of region covariance feature extraction. After finetuning, we achieve substantially better performance than the baseline methods.