Research

What we publish.

Selected papers and notes by our team members. We only list work with a public, verifiable record — conference proceedings or openly accessible documents.

  • WACV 2026 Workshop on Geospatial Computer Vision (GeoCV) · 2026

    Segment Anything but Farms: Comparing Segmentation Paradigms for Rural UAV Captured Ultra-High-Resolution Imagery

    Snehalraj Chugh, Dharmendra Singh Chaudhary, Subash Sigdel, Shubham Thapa, Lalit BC, Nishan Ghimire, Bipendra Basnyat, Nirmalya Roy

    Evaluates promptable segmentation paradigms — including the Segment Anything Model family — against fine-tuned baselines on ultra-high-resolution UAV imagery of rural farmland, where small objects, heavy class imbalance and massive image sizes break assumptions designed for natural photos.

    Computer VisionSegmentationSAMUAV ImageryRemote Sensing

  • Independent research note · 2022

    Classification in Machine Learning

    Subash Sigdel

    A technical overview of classification — learning a function that maps feature sets to predefined class labels — surveying core algorithms and evaluation practice for pattern-recognition tasks.

    Machine LearningClassification