I have two sets of images, say S1 and S2 which are subset of their parent set S (S1 intersection S2 not necessarily equal to 0 and S1 union S2 not necessarily equal S). I want to visualize these sets of images in a UMAP. S1 and S2 are used as training images to train two models, namely M1 and M2 respectively (M1 and M2 have the same model architecture).
The need for visualization of these two sets of images is to check the characteristics these images contain so as to see its corresponding result in the performance. Basically, the effect these images have the model.
Now, my question is to visualize these images, what would be the best possible data to feed to the UMAP?
My idea is to train a model M (same architecture as M1 and M2) with set S and use its features as input to the UMAP as these would help me to visualize the clusters of images which are interpreted as 'similar' by the model. Or is there a better approach?
