Contrastive Fine-grained Class Clustering via Generative Adversarial Networks

Jung-Woo Ha, Yunji Kim

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• naver-ai/c3-gan — marked official in Papers with Code; named in the paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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 https://github.com/naver-ai/c3-gan.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2112.14971")
get_code_for_paper("2112.14971")
have("2112.14971")

Connect an agent — have() is free.