Sheta A, Zinnen M, Sindel A, Maier A, Christlein V (2026)
Publication Type: Conference contribution
Publication year: 2026
Publisher: Springer Science and Business Media Deutschland GmbH
Book Volume: 16169 LNCS
Pages Range: 511-523
Conference Proceedings Title: Lecture Notes in Computer Science
Event location: Rome, ITA
ISBN: 9783032113160
DOI: 10.1007/978-3-032-11317-7_42
Finding smell references in historic artworks is a challenging problem. Beyond artwork-specific challenges such as stylistic variations, their recognition demands exceptionally detailed annotation classes, resulting in annotation sparsity and extreme class imbalance. In this work, we explore the potential of synthetic data generation to alleviate these issues and enable accurate detection of smell-related objects. We evaluate several diffusion-based augmentation strategies and demonstrate that incorporating synthetic data into model training can improve detection performance. Our findings suggest that leveraging the large-scale pretraining of diffusion models offers a promising approach for improving detection accuracy, particularly in niche applications where annotations are scarce and costly to obtain. Furthermore, the proposed approach proves to be effective even with relatively small amounts of data, and scaling it up provides high potential for further enhancements. The source code for data generation and downstream evaluation is available at https://github.com/ultiwinter/MT_DA_LDM_OD.
APA:
Sheta, A., Zinnen, M., Sindel, A., Maier, A., & Christlein, V. (2026). Data Augmentation via Latent Diffusion Models for Detecting Smell-Related Objects in Historical Artworks. In Emanuele Rodolà, Fabio Galasso, Iacopo Masi (Eds.), Lecture Notes in Computer Science (pp. 511-523). Rome, ITA: Springer Science and Business Media Deutschland GmbH.
MLA:
Sheta, Ahmed, et al. "Data Augmentation via Latent Diffusion Models for Detecting Smell-Related Objects in Historical Artworks." Proceedings of the Workshops and competitions hosted by the 23rd International Conference on Image Analysis and Processing, ICIAP 2025, Rome, ITA Ed. Emanuele Rodolà, Fabio Galasso, Iacopo Masi, Springer Science and Business Media Deutschland GmbH, 2026. 511-523.
BibTeX: Download