Metraipolis › archive › dc_2eebd0216bda

Fine-resolution land-use segmentation and synthetic image-label augmentation in the Kathmandu Valley — arXiv:2611.10847

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.10847
License (as archived): CC0-1.0
Archived: 2026-11-10T18:42:51.927Z
SHA-256 of the archived text: 33ea1dc5e92a7c98999a9c09db298f48f25898abdff24219819cde9c23ffa278
Stable URL of this page: https://metraipolis.com/documento/dc_2eebd0216bda

How to cite

Fine-resolution land-use segmentation and synthetic image-label augmentation in the Kathmandu Valley — arXiv:2611.10847 — arXiv (en), https://arxiv.org/abs/2611.10847 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2eebd0216bda (Metraipolis archive dc_2eebd0216bda, sha256 33ea1dc5e92a7c98999a9c09db298f48f25898abdff24219819cde9c23ffa278)

BibTeX

@misc{dc2eebd0216bda,
  title = {Fine-resolution land-use segmentation and synthetic image-label augmentation in the Kathmandu Valley — arXiv:2611.10847},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.10847},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2eebd0216bda; sha256 33ea1dc5e92a7c98999a9c09db298f48f25898abdff24219819cde9c23ffa278},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10847. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Parcel-scale land-use data is missing for most rapidly urbanizing Global South cities, as current segmentation architectures rely on multispectral imagery and planned layouts. We introduce a hand-annotated six-class land-use corpus covering 202 km$^2$ of Kathmandu Valley across 408 fine-resolution RGB scenes. The dataset is uniquely challenging: RGB spectral similarity is high, class imbalance approaches 100:1, and key structural features like rivers measure just two to three pixels wide at a standard hierarchical decoder's prediction stride. Evaluating five architectures reveals that standard random data splitting conceals massive spatial leakage. Switching to a strict sequence-block split drops performance by up to 0.095 mIoU. This penalty exceeds the performance gap between the architectures themselves. We modified the SegFormer baseline by integrating a half-resolution residual detail path, boundary-reliability reweighting, a topology-aware loss, and a presence-balanced sampler. Adding only 1.9% more parameters, the enhanced architecture improves mean IoU across every test fold, with gains concentrated in rare, thin-structure classes. However, both models achieve identical results on the external LoveDA benchmark. Finally, augmenting with diffusion-generated pairs at matched compute degraded accuracy across all architectures, especially harming rare classes it aimed to improve. This demonstrates that blindly incorporating synthetic data can severely damage performance, highlighting a critical need to rigorously evaluate and filter generated samples before training.

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/2611.10847 — 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 2026-11-10T18:37:37.608Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).