Contrastive Fine-grained Class Clustering via Generative Adversarial Networks. (arXiv:2112.14971v2 [cs.CV] UPDATED)

Unsupervised fine-grained class clustering is a practical yet challenging
task due to the difficulty of feature representations learning of subtle object
details. We introduce C3-GAN, a method that leverages the categorical inference
power of InfoGAN with contrastive learning. We aim to learn feature
representations that encourage a dataset to form distinct cluster boundaries in
the embedding space, while also maximizing the mutual information between the
latent code and its image observation. Our approach is to train a
discriminator, which is …

arxiv clustering cv generative adversarial networks networks