On a Quick Way to Extract Concise Image Descriptors from CNN Models

It is our expectation that concise descriptors can be extracted from these feature vectors with the minimal additional overhead of training a few extra layers that can piggy-back on top of these classification models. This can be done by calculating the covariance matrix for the feature vectors calculated from a set of images – resulting in a [1792×1792] matrix. Here are the results:

The raw feature vector, raw-1792, and the full pca transform, pca-1792, do indeed appear to be pretty good descriptors for the image content, at least according to this test.

Source: blog.phash.org