Metraipolis › archive › dc_d27f276747da
TreemapMix: Dirichlet-Controlled Multi-Image Augmentation for Probability and Ordinal Supervision — arXiv:2610.38265
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.38265
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:40:21.697Z
- SHA-256 of the archived text
0308ed271bf39913ed7f240bbb99cc032c161456fd29cd6240ef710dc8ada0c3- Stable URL of this page
https://metraipolis.com/documento/dc_d27f276747da
How to cite
TreemapMix: Dirichlet-Controlled Multi-Image Augmentation for Probability and Ordinal Supervision — arXiv:2610.38265 — arXiv (en), https://arxiv.org/abs/2610.38265 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d27f276747da (Metraipolis archive dc_d27f276747da, sha256 0308ed271bf39913ed7f240bbb99cc032c161456fd29cd6240ef710dc8ada0c3)
BibTeX
@misc{dcd27f276747da,
title = {TreemapMix: Dirichlet-Controlled Multi-Image Augmentation for Probability and Ordinal Supervision — arXiv:2610.38265},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.38265},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d27f276747da; sha256 0308ed271bf39913ed7f240bbb99cc032c161456fd29cd6240ef710dc8ada0c3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38265. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Data augmentation improves visual recognition by exposing models to synthetic training examples that encourage generalization beyond the observed data. Mixed-sample methods extend this idea by combining multiple images. However, many common approaches either mix only pairs of images or rely on fixed small layouts, limiting control over source count, visible area proportions, and induced supervision. We propose TreemapMix, a distribution-controlled multi-image augmentation that samples source weights from a Dirichlet distribution and assigns them to area-proportional regions using a treemap partition. The resulting known region areas support two complementary objectives. TreemapMix with soft cross-entropy (SCE) treats areas as soft class-probability targets, while TreemapMix with a Plackett-Luce (PL) objective converts areas into ordinal supervision. On ImageNet-1K under matched training recipes, TreemapMix-SCE achieves substantially lower calibration error than evaluated mixed-sample baselines, while TreemapMix-PL achieves the strongest Top-1 accuracy. Transfer experiments on object detection and instance segmentation suggest that TreemapMix-pretrained features remain useful beyond classification. These results show that controlled multi-image composition can expose the same region-area information as either probability-matching or rank-matching supervision. Code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.38265 — 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 2026-11-01T02:16:43.873Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).