The Impact of Semi-Supervised Learning on Line Segment Detection

TL;DR

This paper introduces a semi-supervised learning approach for line segment detection in images, achieving comparable results to fully supervised methods and enabling applications with limited labeled data.

Contribution

It is the first to apply modern semi-supervised learning techniques to line detection, improving efficiency and domain adaptation capabilities.

Findings

Comparable performance to fully supervised methods

Effective in domain-specific scenarios like forestry

Suitable for real-time and online applications

Abstract

In this paper we present a method for line segment detection in images, based on a semi-supervised framework. Leveraging the use of a consistency loss based on differently augmented and perturbed unlabeled images with a small amount of labeled data, we show comparable results to fully supervised methods. This opens up application scenarios where annotation is difficult or expensive, and for domain specific adaptation of models. We are specifically interested in real-time and online applications, and investigate small and efficient learning backbones. Our method is to our knowledge the first to target line detection using modern state-of-the-art methodologies for semi-supervised learning. We test the method on both standard benchmarks and domain specific scenarios for forestry applications, showing the tractability of the proposed method.