Update README.md

Author: robmarkcole

README.md

@@ -186,6 +186,7 @@ For multi/hyper-spectral imagery, classical techniques may be used (e.g. k-means
 * [DeepCropMapping](https://github.com/Lab-IDEAS/DeepCropMapping) -> A multi-temporal deep learning approach with improved spatial generalizability for dynamic corn and soybean mapping, uses LSTM
 * [Segment Canopy Cover and Soil using NDVI and Rasterio](https://towardsdatascience.com/segment-satellite-imagery-using-ndvi-and-rasterio-6dcae02a044b)
 * [Use KMeans clustering to segment satellite imagery by land cover/land use](https://towardsdatascience.com/segment-satellite-images-using-rasterio-and-scikit-learn-fc048f465874)
+* [ResUnet-a](https://github.com/Akhilesh64/ResUnet-a) -> Implementation of the paper "ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data" in TensorFlow
 
 ### Semantic segmentation - water, coastlines & floods
 * [UNSOAT used fastai to train a Unet to perform semantic segmentation on satellite imageries to detect water](https://forums.fast.ai/t/unosat-used-fastai-ai-for-their-floodai-model-discussion-on-how-to-move-forward/78468) - [paper](https://www.mdpi.com/2072-4292/12/16/2532) + [notebook](https://github.com/UNITAR-UNOSAT/UNOSAT-AI-Based-Rapid-Mapping-Service/blob/master/Fastai%20training.ipynb), accuracy 0.97, precision 0.91, recall 0.92
@@ -442,6 +443,7 @@ Monitor water levels, coast lines, size of urban areas, wildfire damage, crop ch
 * [DSFANet](https://github.com/rulixiang/DSFANet) -> Unsupervised Deep Slow Feature Analysis for Change Detection in Multi-Temporal Remote Sensing Images
 * [siamese-change-detection](https://github.com/mvkolos/siamese-change-detection) -> Targeted synthesis of multi-temporal remote sensing images for change detection using siamese neural networks
 * [Bi-SRNet](https://github.com/ggsDing/Bi-SRNet) -> Pytorch codes of 'Bi-Temporal Semantic Reasoning for the Semantic Change Detection in HR Remote Sensing Images
+* [RaVAEn](https://github.com/spaceml-org/RaVAEn) -> RaVAEn is a lightweight, unsupervised approach for change detection in satellite data based on Variational Auto-Encoders (VAEs) with the specific purpose of on-board deployment
 
 ## Wealth and economic activity
 The goal is to predict economic activity from satellite imagery rather than conducting labour intensive ground surveys
@@ -474,6 +476,7 @@ The goal is to predict economic activity from satellite imagery rather than cond
 * [forestcasting](https://github.com/ivanzvonkov/forestcasting) -> Forest fire prediction powered by analytics
 * [Hurricane Damage Detection](https://github.com/Ryan-Awad/Hurricane-Damage-Detection) -> A convolutional neural network model used to detect hurricane damage in satellite images
 * [Machine Learning-based Damage Assessment for Disaster Relief on Google AI blog](https://ai.googleblog.com/2020/06/machine-learning-based-damage.html) -> uses object detection to locate buildings, then a classifier to determine if a building is damaged. Challenge of generalising due to small dataset
+* [RaVAEn](https://github.com/spaceml-org/RaVAEn) -> RaVAEn is a lightweight, unsupervised approach for change detection in satellite data based on Variational Auto-Encoders (VAEs) with the specific purpose of on-board deployment
 
 ## Super-resolution
 Super-resolution attempts to enhance the resolution of an imaging system, and can be applied as a pre-processing step to improve the detection of small objects. For an introduction to this topic [read this excellent article](https://bleedai.com/super-resolution-going-from-3x-to-8x-resolution-in-opencv/). Note that super resolution techniques are generally grouped into single image super resolution (SISR) **or** a multi image super resolution (MISR) which is typically applied to video frames.
@@ -531,6 +534,7 @@ Translate images e.g. from SAR to RGB.
 * [How to Develop a Pix2Pix GAN for Image-to-Image Translation](https://machinelearningmastery.com/how-to-develop-a-pix2pix-gan-for-image-to-image-translation/) -> article on machinelearningmastery.com
 * [Satellite-Imagery-to-Map-Translation-using-Pix2Pix-GAN-framework](https://github.com/anh-nn01/Satellite-Imagery-to-Map-Translation-using-Pix2Pix-GAN-framework)
 * [SAR to RGB Translation using CycleGAN](https://www.esri.com/arcgis-blog/products/api-python/imagery/sar-to-rgb-translation-using-cyclegan/) -> uses a CycleGAN model in the ArcGIS API for Python
+* [RSIT_SRM_ISD](https://github.com/summitgao/RSIT_SRM_ISD) -> PyTorch implementation of Remote sensing image translation via style-based recalibration module and improved style discriminator
 
 ## GANS
 * [Anomaly Detection on Mars using a GAN](https://omdena.com/projects/anomaly-detection-mars/)
@@ -540,6 +544,7 @@ Translate images e.g. from SAR to RGB.
 * [CSA-CDGAN](https://github.com/wangle53/CSA-CDGAN) -> CSA-CDGAN: Channel Self-Attention Based Generative Adversarial Network for Change Detection of Remote Sensing Images
 * [DSGAN](https://github.com/lzhengchun/DSGAN) -> a conditinal GAN for dynamic precipitation downscaling
 * [MarsGAN](https://github.com/kheyer/MarsGAN) -> GAN trained on satellite photos of Mars
+* [HC_ADGAN](https://github.com/summitgao/HC_ADGAN) -> codes for the paper Adaptive Dropblock Enhanced GenerativeAdversarial Networks for Hyperspectral Image Classification
 
 ## Adversarial ML
 Efforts to detect falsified images
@@ -564,6 +569,7 @@ Efforts to detect falsified images
 * [GRN-SNDL](https://github.com/jiankang1991/GRN-SNDL) -> model the relations between samples (or scenes) by making use of a graph structure which is fed into network learning
 * [SauMoCo](https://github.com/jiankang1991/SauMoCo) -> codes for TGRS paper: Deep Unsupervised Embedding for Remotely Sensed Images Based on Spatially Augmented Momentum Contrast
 * [TGRS_RiDe](https://github.com/jiankang1991/TGRS_RiDe) -> Rotation Invariant Deep Embedding for RemoteSensing Images
+* [RaVAEn](https://github.com/spaceml-org/RaVAEn) -> RaVAEn is a lightweight, unsupervised approach for change detection in satellite data based on Variational Auto-Encoders (VAEs) with the specific purpose of on-board deployment
 
 ## Few/one/zero/low shot learning
 This is a class of techniques which attempt to make predictions for classes with few, one or even zero examples provided during training. In zero shot learning (ZSL) the model is assisted by the provision of auxiliary information which typically consists of descriptions/semantic attributes/word embeddings for both the seen and unseen classes at train time ([ref](https://learnopencv.com/zero-shot-learning-an-introduction/)). These approaches are particularly relevant to remote sensing, where there may be many examples of common classes, but few or even zero examples for other classes of interest.
@@ -744,6 +750,8 @@ Measure surface contours.
 * [s1_icetype_cnn](https://github.com/nansencenter/s1_icetype_cnn) -> Retrieve sea ice type from Sentinel-1 SAR with CNN
 * [SARSeg](https://github.com/ggsDing/SARSeg) -> pytorch code for the paper 'MP-ResNet: Multi-path Residual Network for the Semantic segmentation of PolSAR Images'
 * [TGRS_DisOptNet](https://github.com/jiankang1991/TGRS_DisOptNet) -> Distilling Semantic Knowledge from Optical Images for Weather-independent Building Segmentation
+* [SAR_CD_DDNet](https://github.com/summitgao/SAR_CD_DDNet) -> PyTorch implementation of Change Detection in Synthetic Aperture Radar Images Using a Dual Domain Network
+* [SAR_CD_MS_CapsNet](https://github.com/summitgao/SAR_CD_MS_CapsNet) -> Code for the paper "Change Detection in SAR Images Based on Multiscale Capsule Network" IEEE GRSL 2021
 
 ## Neural nets in space
 Processing on board a satellite allows less data to be downlinked. e.g. super-resolution image might take 8 images to generate, then a single image is downlinked. Other applications include cloud detection and collision avoidance.