Metraipolis › archive › dc_3f9cfede4f00

Test-Time Augmentation for Tabular-to-Image Classifiers under Distribution Shifts — arXiv:2608.03557

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03557
License (as archived)
CC0-1.0
Archived
2026-10-31T12:43:17.415Z
SHA-256 of the archived text
d1395dec3a21560ff24236c9311b2c130ce99cd1cc8bdeb189c8e8116404b893
Stable URL of this page
https://metraipolis.com/documento/dc_3f9cfede4f00

How to cite

Test-Time Augmentation for Tabular-to-Image Classifiers under Distribution Shifts — arXiv:2608.03557 — arXiv (en), https://arxiv.org/abs/2608.03557 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3f9cfede4f00 (Metraipolis archive dc_3f9cfede4f00, sha256 d1395dec3a21560ff24236c9311b2c130ce99cd1cc8bdeb189c8e8116404b893)
BibTeX
@misc{dc3f9cfede4f00,
  title = {Test-Time Augmentation for Tabular-to-Image Classifiers under Distribution Shifts — arXiv:2608.03557},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03557},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3f9cfede4f00; sha256 d1395dec3a21560ff24236c9311b2c130ce99cd1cc8bdeb189c8e8116404b893},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03557. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tabular-to-image methods that convert tabular data into visual representations have emerged as a novel paradigm for leveraging the high performance of deep learning models. Despite their advantages, the robustness of these methods under distribution shifts remains under explored. Test-Time Augmentation (TTA) is an effective approach in image classification to improve model generalization and robustness, where predictions over multiple transformed views of each input are aggregated. This work evaluates the impact of TTA techniques on predictive performance under Out-Of-Distribution (OOD) for representations generated by tabular-to-image methods. Six tabular-to-image encoding methods were considered: TINTO, IGTD, DeepInsight, BIE, DistanceMatrix, Fotomics. Twenty-five TTA techniques were used, organized into six types: Geometric, Photometric, Structural, Frequency/Encoding, Mixup, and Composite. We employed two datasets from the TableShift benchmark (HELOC and Voting) that provide in-distribution and OOD test subsets designed to evaluate the effect of distribution shifts on tabular data. The results indicate that TTA improves OOD performance, with composite and photometric strategies providing the best trade-off between robustness and variance. In contrast, frequency-domain transformations that alter the encoder's feature-to-intensity mapping consistently degrade performance. These findings highlight TTA as a promising approach for improving the robustness and generalization of classifiers trained on image representations derived from tabular data, particularly under distribution shifts.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.03557 — 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 2026-10-31T12:31:30.419Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).