Abstract
Retraining visual perception pipelines in High-Mix, Low-Volume (HMLV) automotive manufacturing must be carried out under tight annotation, energy, and time budgets, yet most Synthetic Data Generation (SDG) strategies still operate in the thousands of images. This work evaluates Semantically-Guided Domain Randomization (S-GDR), an annotation-free adaptation pipeline that couples Vision-Language Model (VLM)-based semantic captioning of a small unannotated real reference set with diffusion-based background synthesis (Stable Diffusion XL (SDXL) conditioned by ControlNet and IP-Adapter) and mask-based object composition. On an automotive multi-object detection benchmark and with a fixed budget of 200 synthetic training images, S-GDR reaches mAP50-95 = 0.739 on a real held-out test set, outperforming a domain-randomized render baseline (mAP50-95 = 0.697) as well as brightness filtering, perceptual hashing, CycleGAN style transfer, and unguided diffusion variants sharing the same 200-image budget. These initial observations position S-GDR as a promising annotation- free alternative for extreme data-scarcity regimes.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Araya-Martinez, J. M., Mohan, G., & Lambrecht, J. (2026). Semantically-Guided Domain Randomization for Industrial Object Detection in Low-Image-Budget Regimes. https://omanscience.com/en/articles/semantically-guided-domain-randomization-for-industrial-object-detection-in-low-image-budget-regimes
MLA 9
Araya-Martinez, Jose Moises, et al. "Semantically-Guided Domain Randomization for Industrial Object Detection in Low-Image-Budget Regimes." https://omanscience.com/en/articles/semantically-guided-domain-randomization-for-industrial-object-detection-in-low-image-budget-regimes.
Chicago (author–date)
Araya-Martinez, Jose Moises, Gautham Mohan, and Jens Lambrecht. 2026. "Semantically-Guided Domain Randomization for Industrial Object Detection in Low-Image-Budget Regimes." https://omanscience.com/en/articles/semantically-guided-domain-randomization-for-industrial-object-detection-in-low-image-budget-regimes.
Harvard
Araya-Martinez, J. M., Mohan, G. and Lambrecht, J. (2026) 'Semantically-Guided Domain Randomization for Industrial Object Detection in Low-Image-Budget Regimes', Available at: https://omanscience.com/en/articles/semantically-guided-domain-randomization-for-industrial-object-detection-in-low-image-budget-regimes.
Vancouver
Araya-Martinez JM, Mohan G, Lambrecht J. Semantically-Guided Domain Randomization for Industrial Object Detection in Low-Image-Budget Regimes. https://omanscience.com/en/articles/semantically-guided-domain-randomization-for-industrial-object-detection-in-low-image-budget-regimes
IEEE
J. M. Araya-Martinez, G. Mohan, and J. Lambrecht, "Semantically-Guided Domain Randomization for Industrial Object Detection in Low-Image-Budget Regimes," https://omanscience.com/en/articles/semantically-guided-domain-randomization-for-industrial-object-detection-in-low-image-budget-regimes.