CAD Models to Real-World Images: A Practical Approach to Unsupervised Domain Adaptation in Industrial Object Classification

TL;DR

This paper presents a practical unsupervised domain adaptation pipeline that effectively transfers knowledge from CAD models to real-world images for industrial object classification, outperforming existing methods especially on industrial datasets.

Contribution

It introduces a systematic analysis of domain adaptation strategies tailored for industrial settings using CAD models, providing new guidelines and achieving state-of-the-art results on industrial datasets.

Findings

Achieves state-of-the-art performance on VisDA benchmark.

Significantly improves recognition on industrial dataset with 102 mechanical parts.

Provides practical guidelines for applying unsupervised domain adaptation in industry.

Abstract

In this paper, we systematically analyze unsupervised domain adaptation pipelines for object classification in a challenging industrial setting. In contrast to standard natural object benchmarks existing in the field, our results highlight the most important design choices when only category-labeled CAD models are available but classification needs to be done with real-world images. Our domain adaptation pipeline achieves SoTA performance on the VisDA benchmark, but more importantly, drastically improves recognition performance on our new open industrial dataset comprised of 102 mechanical parts. We conclude with a set of guidelines that are relevant for practitioners needing to apply state-of-the-art unsupervised domain adaptation in practice. Our code is available at https://github.com/dritter-bht/synthnet-transfer-learning.