update readme

README.md

@@ -16,7 +16,7 @@ The **trained model** from the main experiments of our publication can be downlo
  - **Setup this Repository**
  - Getting Started: Predict Attribution Maps using the Trained Model from the Article
  - Train Your Own Model
- - **Install via pip**
+ - Install via pip
 
 
 ## Code Structure
@@ -41,15 +41,15 @@ If you apply it to the last convolutional layer, high-level features will be con
 We propose a neural network (NN) architecture to obtain both high-level features in high resolution.
 It consists of an image-to-image network (U-Net) and a task-specific head (regressor or classifier):
 
-<img src="readme/nn_architecture.png">
+<img src="readme/nn_architecture.png" width="1000">
 
 Further, we harmonize the attributions across the training data to obtain consistent results across large and different scenes.
 
-<img src="readme/harmonizing_attributions.png">
+<img src="readme/harmonizing_attributions.png" width="1000">
 
 Our methodology works with a wide range of attribution methods.
 
-<img src="readme/comparing_methods.png">
+<img src="readme/comparing_methods.png" width="1000">
 
 We use our methodology to find patterns of protected and anthropogenic areas as proxies for naturalness and human influence, respectively.
 To this end, we use the AnthroProtect dataset which is built to discover the appearance of wilderness and anthropogenic areas in Fennoscandia using multispectral satellite imagery.