Update README.md

README.md

@@ -445,6 +445,8 @@ Note that deforestation detection may be treated as a segmentation task or a cha
 
   2.2.56. [cvpr-multiearth-deforestation-segmentation](https://github.com/h2oai/cvpr-multiearth-deforestation-segmentation) -> multimodal Unet entry to the CVPR Multiearth 2023 deforestation challenge
 
+  2.2.57. [supervised-wheat-classification-using-pytorchs-torchgeo](https://medium.com/@sulemanhamdani10/supervised-wheat-classification-using-pytorchs-torchgeo-combining-satellite-imagery-and-python-fc7f95c82e) -> Article: supervised wheat classification using torchgeo `BEGINNER`
+
 
 ### 2.3. Segmentation - Water, coastlines & floods
 
@@ -1386,6 +1388,8 @@ Detecting the most noticeable or important object in a scene
 
   4.6.37. [xView3-The-First-Place-Solution](https://github.com/BloodAxe/xView3-The-First-Place-Solution) - A winning solution for [xView 3](https://iuu.xview.us/) challenge (Vessel detection, classification and length estimation on Sentinetl-1 images). Contains trained models, inference pipeline and training code & configs to reproduce the results.
 
+  4.6.38. [vessel-detection-viirs](https://github.com/allenai/vessel-detection-viirs) -> Model and service code for streaming vessel detections from VIIRS satellite imagery
+
 ### 4.7. Object detection - Cars, vehicles & trains
 
   4.7.1. [Detection of parkinglots and driveways with retinanet](https://github.com/spiyer99/retinanet) `BEGINNER`
@@ -1614,6 +1618,8 @@ A variety of techniques can be used to count animals, including object detection
 
   4.12.53. [OAN](https://github.com/Ranchosky/OAN) code for paper: Fewer is More: Efficient Object Detection in Large Aerial Images, based on MMdetection
 
+  4.12.54. [DOTA-C](https://github.com/hehaodong530/DOTA-C) -> evaluating the robustness of object detection models to 19 types of image quality degradation
+
 
 ## 5. Object counting
 When the object count, but not its shape is required, U-net can be used to treat this as an image-to-image translation problem.
@@ -2053,6 +2059,8 @@ Change detection is a vital component of remote sensing analysis, enabling the m
 
   8.125. [CGNet-CD](https://github.com/ChengxiHAN/CGNet-CD) -> code for 2023 paper: Change Guiding Network: Incorporating Change Prior to Guide Change Detection in Remote Sensing Imagery
 
+  8.126. [PA-Former](https://github.com/liumency/PA-Former) -> code for 2022 paper: PA-Former: Learning Prior-Aware Transformer for Remote Sensing Building Change Detection
+
 #
 ## 9. Time series
 
@@ -2340,7 +2348,7 @@ Note that nearly all the MISR publications resulted from the [PROBA-V Super Reso
 
   14.1.15. [PROBA-V-Super-Resolution](https://github.com/spicy-mama/PROBA-V-Super-Resolution) -> solution using a custom deep learning architecture
 
-
+  14.1.16. [satlas-super-resolution](https://github.com/allenai/satlas-super-resolution) -> Satlas Super Resolution: model is an adaptation of ESRGAN, with changes that allow the input to be a time series of Sentinel-2 images.
 
 ### 14.2. Single image super-resolution (SISR)
 
@@ -2588,6 +2596,8 @@ Image-to-image translation is a crucial aspect of computer vision that utilizes
 
   16.16. [pix2pix-GANs](https://github.com/shashi7679/pix2pix-GANs) -> Generate Map using Satellite Image & PyTorch
 
+  16.17. [map-sat](https://github.com/miquel-espinosa/map-sat) -> code for 2023 paper: Generate Your Own Scotland: Satellite Image Generation Conditioned on Maps
+
 
 #
 ## 17. Data fusion
@@ -2941,6 +2951,8 @@ This is a class of techniques which attempt to make predictions for classes with
 
   24.13. [SiameseNet-for-few-shot-Hyperspectral-Classification](https://github.com/jjwwczy/jjwwczy-SiameseNet-for-few-shot-Hyperspectral-Classification) -> code for 2020 paper: 3DCSN:SiameseNet-for-few-shot-Hyperspectral-Classification
 
+  24.14. [MESSL](https://github.com/OMEGAFSL/MESSL) -> code for paper: Multiform Ensemble Self-Supervised Learning for Few-Shot Remote Sensing Scene Classification
+
 #
 ## 25. Self-supervised, unsupervised & contrastive learning
 Self-supervised, unsupervised & contrastive learning are all methods of machine learning that use unlabeled data to train algorithms. Self-supervised learning uses labeled data to create an artificial supervisor, while unsupervised learning uses only the data itself to identify patterns and similarities. Contrastive learning uses pairs of data points to learn representations of data, usually for classification tasks.
@@ -3475,6 +3487,8 @@ Image quality describes the degree of accuracy with which an image can represent
 
   36.17. [lvrnet](https://github.com/Achleshwar/lvrnet) -> Lightweight Image Restoration for Aerial Images under Low Visibility
 
+  36.18. [DOTA-C](https://github.com/hehaodong530/DOTA-C) -> evaluating the robustness of object detection models to 19 types of image quality degradation
+
 #
 ## 37. Synthetic data
 Training data can be hard to acquire, particularly for rare events such as change detection after disasters, or imagery of rare classes of objects. In these situations, generating synthetic training data might be the only option. This has become quite sophisticated, with 3D models being use with open source games engines such as [Unreal](https://www.unrealengine.com/en-US/).