cs.CVNov 7, 2026

Fine-resolution land-use segmentation and synthetic image-label augmentation in the Kathmandu Valley

Authors: Pranil Parajuli, Sugam Dahal, Kiran Chandra Dahal

Organizations: Department of Electronics and Computer Engineering, Institute of Engineering, Thapathali Campus, Tribhuvan University, Kathmandu, 44600, Bagmati Province, Nepal

Abstract

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 km2^2 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.

Figures & tables

Explore similar work

CardsList
  1. What Makes Synthetic Data Effective in Image Segmentation

    May 19, 2026Jinjin Zhang, Xiefan Guo, Yizhou Jin +2Synthetic Data AugmentationImage Segmentation

  2. Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models

    Jun 30, 2026Nikolai Röhrich, Julian Gleißner, Ahmed H. A. Ibrahim +2Synthetic Data AugmentationSemantic Segmentation

  3. Grounding Synthetic Data Generation With Vision and Language Models

    Mar 10, 2026Ümit Mert Çağlar, Alptekin TemizelSynthetic Data AugmentationSynthetic Data Evaluation