The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Google Research

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

LAVIS - A One-stop Library for Language-Vision Intelligence

This project reproduces the book Dive Into Deep Learning (https://d2l.ai/), adapting the code from MXNet into PyTorch.

Segment Anything in Medical Images

This is code of book "Learn Deep Learning with PyTorch"

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

OneFormer: One Transformer to Rule Universal Image Segmentation, arxiv 2022 / CVPR 2023

deeplearning.ai , By Andrew Ng, All slide and notebook + data + solutions and video link

机械臂+大模型+多模态=人机协作具身智能体

Referring Expression Datasets API

Earth observation tools for Meta AI Segment Anything

[ECCV2022, TPAMI2023] FAST-VQA, and its extended version FasterVQA.

Project to train/test convolutional neural networks to extract buildings from SpaceNet satellite imageries.

Experiments on Flood Segmentation on Sentinel-1 SAR Imagery with Cyclical Pseudo Labeling and Noisy Student Training

Single Hyperspectral Image Denoising, Inpainting, Super-Resolution

unet for image segmentation

[TGRS 2019] Unsupervised Deep Slow Feature Analysis for Change Detection in Multi-Temporal Remote Sensing Images

Code examples for the book chapter "Supervised, Semi-Supervised and Unsupervised Learning for Hyperspectral Regression".

This repository contains a PyTorch implementation of a U-Net model for segmenting water areas (flood and permananet water) in Sentinel-1 satellite images.

Soil parameter estimation from hyperspectral satellite images

This is a [forked version] for author's debugging. Please jump to https://github.com/QualityAssessment/DOVER for stable version to use.

Pytorch Tutorials, Exercise, Models

A simple and light CNN-based regression model for soil parameters estimation from hyperspectral images.