PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

Adapting Meta AI's Segment Anything to Downstream Tasks with Adapters and Prompts

This is the pytorch implement of our paper "RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model"

[CVPR 2021] CPS: Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision

The net:cal calibration framework is a Python 3 library for measuring and mitigating miscalibration of uncertainty estimates, e.g., by a neural network.

[CVPR23] Official Implementation of MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation

A QGIS plugin tool using Segment Anything Model (SAM) to accelerate segmenting or delineating landforms in geospatial raster images.

Implement some models of RGB/RGBD semantic segmentation in PyTorch, easy to run. Such as FCN, RefineNet, PSPNet, RDFNet, 3DGNN, PointNet, DeepLab V3, DeepLab V3 plus, DenseASPP, FastFCN

The implementation of "Bootstrapping Semantic Segmentation with Regional Contrast" [ICLR 2022].

Fine-tuning SAM with Multi-Modal Prompts for Mobility Infrastructure Segmentation

Visualization library for well-known-text strings and shapely geometries.

ReCo Dataset, the dataset files can be found at https://www.kaggle.com/datasets/fdudsde/reco-dataset.

Convert geospatial datasets of shapefiles and rasters into COCO format datasets of images and JSON.