Merge branch 'main' of https://github.com/KimForss/azure-docs-pr

Author: Kimmo Forss

articles/active-directory-b2c/technicalprofiles.md

@@ -249,7 +249,7 @@ The **InputClaim** element contains the following attributes:
 | --------- | -------- | ----------- |
 | ClaimTypeReferenceId | Yes | The identifier of a claim type. The claim is already defined in the claims schema section in the policy file or parent policy file. |
 | DefaultValue | No | A default value to use to create a claim if the claim indicated by ClaimTypeReferenceId doesn't exist so that the resulting claim can be used as an InputClaim element by the technical profile. |
-|AlwaysUseDefaultValue |No |Forces the use of the default value. |
+|AlwaysUseDefaultValue |Yes |Forces the use of the default value. |
 | PartnerClaimType | No | The identifier of the claim type of the external partner that the specified policy claim type maps to. If the PartnerClaimType attribute isn't specified, the specified policy claim type is mapped to the partner claim type of the same name. Use this property when your claim type name is different from the other party. An example is if the first claim name is *givenName*, while the partner uses a claim named *first_name*. |
 
 ## Display claims

articles/advisor/media/view-recommendations/new-configuration-m.png

@@ -27,6 +27,9 @@ This feature provides two possible outputs based on the customer's needs:
 
 This service is currently in preview, and the API may change in the future.
 
+> [!IMPORTANT]
+> Background removal is only available in the following Azure regions: East US, France Central, Korea Central, North Europe, Southeast Asia, West Europe, West US.
+
 ## Background removal examples
 
 The following example images illustrate what the Image Analysis service returns when removing the background of an image and creating an alpha matte. 

articles/advisor/media/view-recommendations/new-filtering-m.png

@@ -76,7 +76,7 @@ To train a model with your own dataset, the dataset should be arranged in the CO
 
 ### Dataset annotation format
 
-Image Analysis uses the COCO file format for indexing/organizing the training images and their annotations. Below are examples and explanations of what specific format is needed for multiclass classification and object detection.
+Image Analysis uses the COCO file format for indexing/organizing the training images and their annotations. Below are examples and explanations of what specific format is needed for classification and object detection.
 
 Image Analysis model customization for classification is different from other kinds of vision training, as we utilize your class names, as well as image data, in training. So, be sure provide meaningful category names in the annotations.
 
@@ -260,9 +260,7 @@ You need to upload your training images to an Azure Blob Storage container. Go t
 
 To train a custom model, you need to associate it with a **Dataset** where you provide images and their label information as training data. In Vision Studio, select the **Datasets** tab to view your datasets.
 
-To create a new dataset, select **add new dataset**. Enter a name and select a dataset type: If you'd like to do image classification, select `Multi-class image classification`. If you'd like to do object detection, select `Object detection`.
-
-
+To create a new dataset, select **add new dataset**. In the popup window, enter a name and select a dataset type for your use case. **Image classification** models apply content labels to the entire image, while **Object detection** models apply object labels to specific locations in the image. **Product recognition** models are a subcategory of object detection models that are optimized for detecting retail products.
 
 ![Choose Blob Storage]( ../media/customization/create-dataset.png)