Invariant information clustering for unsupervised image classification and segmentation

We present a novel clustering objective that learns a neural network classifier from scratch, given only unlabelled data samples. The model discovers clusters that accurately match semantic classes, achieving state-of-the-art results in eight unsupervised clustering benchmarks spanning image classif...

Täydet tiedot

Bibliografiset tiedot
Päätekijät: Ji, X, Henriques, J, Vedaldi, A
Aineistotyyppi: Conference item
Kieli:English
Julkaistu: IEEE 2020