Contrastive Fine-grained Class Clustering via Generative Adversarial NetworksDownload PDF

Published: 28 Jan 2022, Last Modified: 13 Feb 2023ICLR 2022 SpotlightReaders: Everyone
Keywords: Unsupervised Fine-grained Class Clustering, Disentangled Representation Learning, Generative Adversarial Networks
Abstract: 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 also used for inferring clusters, to optimize the contrastive loss, where image-latent pairs that maximize the mutual information are considered as positive pairs and the rest as negative pairs. Specifically, we map the input of a generator, which was sampled from the categorical distribution, to the embedding space of the discriminator and let them act as a cluster centroid. In this way, C3-GAN succeeded in learning a clustering-friendly embedding space where each cluster is distinctively separable. Experimental results show that C3-GAN achieved the state-of-the-art clustering performance on four fine-grained image datasets, while also alleviating the mode collapse phenomenon. Code is available at
One-sentence Summary: We proposed a method for unsupervised fine-grained class clustering that leverages the information-theoretic regularization term based on contrastive loss.
14 Replies