scabini / RADAM
View external linksLinks

We propose a new method named Random encoding of Aggregated Deep Activation Maps (RADAM) for feature extraction from pre-trained Deep CNNs. The technique consists of encoding the output at different depths of the CNN using a Randomized Autoencoder, producing a single image descriptor
39Dec 17, 2024Updated last year

Alternatives and similar repositories for RADAM

Users that are interested in RADAM are comparing it to the libraries listed below

Sorting:

Are these results useful?