Metraipolis › archive › dc_31aefe74115c
Image Augmentation as Test Generation for Deep Learning-Based Image Retrieval Systems — arXiv:2608.27502
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.27502
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T11:14:02.249Z
- SHA-256 of the archived text
b29b58c8b1392bb2c2ec93916e8b2c54d1edf5972be26401d87aaf5457ce4ca0- Stable URL of this page
https://metraipolis.com/documento/dc_31aefe74115c
How to cite
Image Augmentation as Test Generation for Deep Learning-Based Image Retrieval Systems — arXiv:2608.27502 — arXiv (en), https://arxiv.org/abs/2608.27502 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_31aefe74115c (Metraipolis archive dc_31aefe74115c, sha256 b29b58c8b1392bb2c2ec93916e8b2c54d1edf5972be26401d87aaf5457ce4ca0)
BibTeX
@misc{dc31aefe74115c,
title = {Image Augmentation as Test Generation for Deep Learning-Based Image Retrieval Systems — arXiv:2608.27502},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.27502},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_31aefe74115c; sha256 b29b58c8b1392bb2c2ec93916e8b2c54d1edf5972be26401d87aaf5457ce4ca0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27502. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Ensuring the reliability of deep learning-based image retrieval systems is a software engineering challenge. This paper presents a dual contribution: (1) a literature review of augmentation and generation techniques which resulted in the identification of 50 techniques which we organized into a ten-category taxonomy, and (2) a large-scale empirical study that evaluates these techniques as test generators for embedding-based image retrieval systems. Augmented images are embedded using Amazon Titan and OpenCLIP, and evaluated across four analytical dimensions: (1) embedding-space similarity, (2) embedding uncertainty measured via four estimators, (3) semantic realism scored by LLaVA, and (4) retrieval failure rate. Experiments are performed on three datasets: CIFAR-10, ImageNet-1K, and a dataset from an industrial partner (March Networks). Across all evaluated datasets and embedding models, and under the single severity level tested for each technique, weather simulation and SaSPA are the image augmentation/generation techniques that produce the highest embedding uncertainty and failure rates while maintaining a favorable balance between performance stability, visual realism, and augmentation effectiveness. The results we discuss are configuration-specific and may shift under milder or stronger perturbation settings. In contrast, GAN-based augmentation techniques are among the lowest in realism, indicating the presence of synthetic artifacts and perceptual inconsistencies that reduce their suitability to produce realistic test inputs. Overall, our findings provide practical guidelines for selecting augmentation techniques that maximize test diversity while preserving realistic image characteristics, thereby enabling the construction of comprehensive and effective test suites for image retrieval systems while reducing the cost of manual data labeling through the use of metamorphic testing. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-31 in cs.SE). Categorie arXiv: Software Engineering (cs.SE) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.27502 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T10:56:43.368Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).