A bunch of LandCoverAI experiments

scratch space to examine coupling coarser scale flows to high res hydrography

[CVPR 2023] Official implementation of the paper "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation"

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

The Python Dict that's better than heroin.

mIOU=80.02 on cityscapes. My implementation of deeplabv3+ (also know as 'Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation' based on the dataset of cityscapes).

Code for Neural Plasticity-Inspired Foundation Model for Observing the Earth Crossing Modalities

The awesome document factory

UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery, ISPRS. Also, including other vision transformers and CNNs for satellite, aerial image …

Accelerated deep learning R&D

UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery, ISPRS. Also, including other vision transformers and CNNs for satellite, aerial image …

Regularization of Building Boundaries using Adversarial and Regularized losses

We propose a simple yet efficient technique to leverage semantic segmentation model to extract and separate individual buildings in densely compacted areas using medium resolution satellite/UAV ort…

Pytorch Bayesian UNet model for segmentation and uncertainty prediction

Implementation of Hang et al. 2020 "Hyperspectral Image Classification with Attention Aided CNNs" for tree species prediction

Python Package for Airborne RGB machine learning

Q. Liu, L. Xiao, J. Yang and Z. Wei, "CNN-Enhanced Graph Convolutional Network With Pixel- and Superpixel-Level Feature Fusion for Hyperspectral Image Classification," in IEEE Transactions on Geosc…

Code of paper 《Remote Sensing Image Scene Classification Based on an Enhanced Attention Module》

High-Resolution Boundary Constrained and Context Enhanced Network for Remote Sensing Image Segmentation

An Earth Engine based landcover mapping tool for the Polesia region, built for the British Trust for Ornithology by Artio Earth Observation.

Code for Landcover mapping with Google Earth Engina + Geemap + Pyhton library and codes

The U-Net architecture CNN Model is developed in python for Land Cover Classification from Very High Resolution Imagery.

[RSE 2022] Cross-sensor domain adaptation for high-spatial resolution urban land-cover mapping: from airborne to spaceborne imagery

The official implementation for NeurIPS2023 paper "SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations"

Dynamic Convolution Self-Attention Network for Land Cover Classification in VHR Remote Sensing Images