Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection

TL;DR

This paper introduces a self-supervised visual prompting framework for cross-domain road damage detection, enabling robust zero-shot transfer and adaptation without labeled data, improving over existing methods in domain generalization.

Contribution

The paper proposes extit{ extbf{ extcolor{blue}{PROBE}}}, a novel self-supervised prompting approach with SPEM and DAPA modules, enhancing cross-domain detection without labels, a significant advancement over prior supervised and self-supervised methods.

Findings

Outperforms supervised and self-supervised baselines across four benchmarks.

Achieves robust zero-shot transfer and domain adaptation.

Demonstrates high data efficiency in few-shot scenarios.

Abstract

The deployment of automated pavement defect detection is often hindered by poor cross-domain generalization. Supervised detectors achieve strong in-domain accuracy but require costly re-annotation for new environments, while standard self-supervised methods capture generic features and remain vulnerable to domain shift. We propose \ours, a self-supervised framework that \emph{visually probes} target domains without labels. \ours introduces a Self-supervised Prompt Enhancement Module (SPEM), which derives defect-aware prompts from unlabeled target data to guide a frozen ViT backbone, and a Domain-Aware Prompt Alignment (DAPA) objective, which aligns prompt-conditioned source and target representations. Experiments on four challenging benchmarks show that \ours consistently outperforms strong supervised, self-supervised, and adaptation baselines, achieving robust zero-shot transfer, improved resilience to domain variations, and high data efficiency in few-shot adaptation. These results highlight self-supervised prompting as a practical direction for building scalable and adaptive visual inspection systems. Source code is publicly available: https://github.com/xixiaouab/PROBE/tree/main