Analyze job allows model performance analysis by comparing the ground truth and predictions and presenting this in a plot where points cluster together based on the model performance characteristics (e.g., points with similar model error form a cluster). A similarity search can be run in two modes for such a job.
Default: The search looks for the same images that match the model performance characteristics of the search candidate set images.
Content: The search looks for the same images that match the visual content of the search candidate set images.
In the default mode, where the Content option is toggled off, the search results show images with similar model performance characteristics. In the below example, the search returned those images with a cow being predicted without it being present in the ground truth annotation.
When the Content options is turned on, it can be seen that the search results are returning visually similar images with the objects matching the content of the image. The results displayed images with similar position and appearance, and not necessarily cow as an object, as shown below.
When 'Content' is turned on, if the underlying dataset was created with a 'Patch' featurizer selected, you will get an option to do a patch feature-based search.