Invariant Information Clustering for Unsupervised Image Classification and Segmentation — mentioned by fxtentacle

Mon, 03 Feb 2020 10:45:41 GMT

The problem that I see with supervised training of a linear classifier after unsupervised training is that if the unsupervised network is large enough, it allows the supervised trainer to choose the working components. As shown in [1] that can lead to randomly initialized networks working well, too, meaning that this does not necessarily show that the unsupervised training produced useful features. I would instead suggest to train a categorization classifier unsupervised, too, for example using mutual information loss with the correct number of categories, as suggested in [2]. Afterwards, one…

Paper and discussion history. A mention is not an endorsement.

Invariant Information Clustering for Unsupervised Image Classification and Segmentation · HackerPapers discussions

Invariant Information Clustering for Unsupervised Image Classification and Segmentation — mentioned by fxtentacle