Sim-to-Real Domain Adaptation for Deformation Classification

TL;DR

This paper presents a novel framework that uses synthetic data and an adapter network to improve deformation classification in computer vision, effectively bridging the gap between simulated and real-world data.

Contribution

It introduces a new method combining synthetic data generation with an adapter network for effective sim-to-real domain adaptation in deformation classification.

Findings

Improved classification accuracy on real-world data.

Effective domain adaptation without real deformed object data.

Enhanced simulation-based training for deformation detection.

Abstract

Deformation detection is vital for enabling accurate assessment and prediction of structural changes in materials, ensuring timely and effective interventions to maintain safety and integrity. Automating deformation detection through computer vision is crucial for efficient monitoring, but it faces significant challenges in creating a comprehensive dataset of both deformed and non-deformed objects, which can be difficult to obtain in many scenarios. In this paper, we introduce a novel framework for generating controlled synthetic data that simulates deformed objects. This approach allows for the realistic modeling of object deformations under various conditions. Our framework integrates an intelligent adapter network that facilitates sim-to-real domain adaptation, enhancing classification results without requiring real data from deformed objects. We conduct experiments on domain adaptation and classification tasks and demonstrate that our framework improves sim-to-real classification results compared to simulation baseline.