Road Disease Detection based on Latent Domain Background Feature Separation and Suppression

TL;DR

This paper introduces LDBFSS, a novel network that enhances road disease detection by unsupervised background feature separation and contrastive learning, integrated with YOLOv5, showing significant accuracy improvements.

Contribution

The paper proposes a new LDBFSS network that performs background feature suppression without domain supervision and enhances disease features using contrastive learning, improving detection accuracy.

Findings

Nearly 4% accuracy increase on GRDDC dataset

4.6% accuracy increase on CNRDD dataset

Proven effectiveness and superiority over existing models

Abstract

Road disease detection is challenging due to the the small proportion of road damage in target region and the diverse background,which introduce lots of domain information.Besides, disease categories have high similarity,makes the detection more difficult. In this paper, we propose a new LDBFSS(Latent Domain Background Feature Separation and Suppression) network which could perform background information separation and suppression without domain supervision and contrastive enhancement of object features.We combine our LDBFSS network with YOLOv5 model to enhance disease features for better road disease detection. As the components of LDBFSS network, we first design a latent domain discovery module and a domain adversarial learning module to obtain pseudo domain labels through unsupervised method, guiding domain discriminator and model to train adversarially to suppress background information. In addition, we introduce a contrastive learning module and design k-instance contrastive loss, optimize the disease feature representation by increasing the inter-class distance and reducing the intra-class distance for object features. We conducted experiments on two road disease detection datasets, GRDDC and CNRDD, and compared with other models,which show an increase of nearly 4% on GRDDC dataset compared with optimal model, and an increase of 4.6% on CNRDD dataset. Experimental results prove the effectiveness and superiority of our model.