Gradient Driven Learning for Pooling in Visual Pipeline Feature Extraction Models

TL;DR

This paper introduces a gradient-based method to optimize pooling maps in visual feature extraction models, replacing manual hyper-parameter tuning with learned parameters to improve classification accuracy.

Contribution

It proposes a novel approach to learn pooling functions via supervised gradient signals, automating a previously manual design choice in visual pipelines.

Findings

Moderate improvements in classification accuracy observed.

Identifies key regions in feature space influencing performance.

Demonstrates potential for automated hyper-parameter tuning.

Abstract

Hyper-parameter selection remains a daunting task when building a pattern recognition architecture which performs well, particularly in recently constructed visual pipeline models for feature extraction. We re-formulate pooling in an existing pipeline as a function of adjustable pooling map weight parameters and propose the use of supervised error signals from gradient descent to tune the established maps within the model. This technique allows us to learn what would otherwise be a design choice within the model and specialize the maps to aggregate areas of invariance for the task presented. Preliminary results show moderate potential gains in classification accuracy and highlight areas of importance within the intermediate feature representation space.