Independent publisher

Lam Tran

lammtfkday

Models in Library0

Datasets in Library2

Models on Hugging Face1

Followers1

Compare the published evidence

This profile connects the 2 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.

Published tasks: Image segmentation.

Reported licenses: cc-by-nc-4.0, mit. Open a record to review its specific license and conditions.

Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.

Datasets

Dataset · Image segmentation

deepglobe-roads

Lam Tran

The DeepGlobe Road Extraction Dataset consists of 6,226 optical satellite images with a spatial dimension of $1024 \times 1024$ pixels and a Ground Sampling Distance (GSD) of 0.5 m/pixel. The imagery spans varied urban, suburban, and rural terrains across Thailand, Indonesia, and India. This repository hosts the standardized, reproducible benchmark partition: Partitioning is constructed deterministically with seed 42 from the sorted filename collection. If you use this dataset in your research, please cite the original challenge paper

Publicly accessible cc-by-nc-4.0 1K<n<10K

View dataset

Dataset · Image segmentation

massachusetts-roads

Lam Tran

High-resolution aerial imagery benchmark for remote sensing road extraction, based on the canonical Massachusetts Roads dataset introduced by Volodymyr Mnih (2013). The Massachusetts Roads Dataset covers diverse urban, suburban, coastal, and forested rural environments throughout the Commonwealth of Massachusetts. Standard benchmark partition for road extraction research: If you use this dataset in your research, please cite

Publicly accessible mit n<1K

View dataset