Metraipolis › archive › dc_e9725672fc82
TopoDPO: Dense Preference Alignment for Structure-Sensitive Aerial Referring Segmentation — arXiv:2611.01551
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01551
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:35:57.454Z
- SHA-256 of the archived text
f9a2673118ec617de3d2b40836c1abab023f37935ea50a48fc6d4afbb19007cb- Stable URL of this page
https://metraipolis.com/documento/dc_e9725672fc82
How to cite
TopoDPO: Dense Preference Alignment for Structure-Sensitive Aerial Referring Segmentation — arXiv:2611.01551 — arXiv (en), https://arxiv.org/abs/2611.01551 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e9725672fc82 (Metraipolis archive dc_e9725672fc82, sha256 f9a2673118ec617de3d2b40836c1abab023f37935ea50a48fc6d4afbb19007cb)
BibTeX
@misc{dce9725672fc82,
title = {TopoDPO: Dense Preference Alignment for Structure-Sensitive Aerial Referring Segmentation — arXiv:2611.01551},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01551},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e9725672fc82; sha256 f9a2673118ec617de3d2b40836c1abab023f37935ea50a48fc6d4afbb19007cb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01551. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Preference optimization for multimodal segmentation faces a granularity mismatch: dense masks contain spatially heterogeneous preference signals, whereas image-level objectives assign one shared nonlinear weight to all spatial margins. We introduce TopoDPO, a topology-aware dense preference alignment framework for structure-sensitive aerial referring segmentation. Topo-Prior mines informative preference pairs using connected-component discrepancy and macro-corner recall, while the dense objective applies the preference penalty to each local margin before spatial aggregation against a frozen supervised reference. On Topo-RS-Hard, a 4590-instance structural stress set, TopoDPO improves intersection over union (IoU) from 50.91% to 51.24% over image-level direct preference optimization (DPO) and reduces Betti-0 error from 1.34 to 0.90; paired image-cluster bootstrap intervals against image-level DPO exclude zero for all five reported metrics. Matched supervised controls and a complete factorial analysis separate the effects of topology-aware pair mining, localized correction, and dense reference-relative preference weighting. An unfiltered stratification over all 39,244 validation records further shows the clearest structural gains on samples with moderate or severe pre-alignment component-count errors. The code is publicly available at: this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.01551 — 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 2026-11-03T10:29:48.779Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).