Contrastive Fine-grained Class Clustering via Generative Adversarial Networks

12/30/2021
by   Yunji Kim, et al.
0

Unsupervised fine-grained class clustering is 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 by applying contrastive learning. We aim to learn feature representations that encourage the data to form distinct cluster boundaries in the embedding space, while also maximizing the mutual information between the latent code and its observation. Our approach is to train the discriminator, which is used for inferring clusters, to optimize the contrastive loss, where the 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 the generator, which has 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 achieved to learn a clustering-friendly embedding space where each cluster is distinctively separable. Experimental results show that C3-GAN achieved state-of-the-art clustering performance on four fine-grained benchmark datasets, while also alleviating the mode collapse phenomenon.

READ FULL TEXT

page 2

page 8

page 9

page 15

page 16

page 17

page 18

research
09/13/2023

Instance Adaptive Prototypical Contrastive Embedding for Generalized Zero Shot Learning

Generalized zero-shot learning(GZSL) aims to classify samples from seen ...
research
07/20/2021

Boosting few-shot classification with view-learnable contrastive learning

The goal of few-shot classification is to classify new categories with f...
research
11/23/2021

Exploring Non-Contrastive Representation Learning for Deep Clustering

Existing deep clustering methods rely on contrastive learning for repres...
research
06/08/2023

Contrastive Representation Disentanglement for Clustering

Clustering continues to be a significant and challenging task. Recent st...
research
08/03/2022

Mutual Information Scoring: Increasing Interpretability in Categorical Clustering Tasks with Applications to Child Welfare Data

Youth in the American foster care system are significantly more likely t...
research
09/07/2022

Information Maximization for Extreme Pose Face Recognition

In this paper, we seek to draw connections between the frontal and profi...
research
05/02/2019

Clustering Images by Unmasking - A New Baseline

We propose a novel agglomerative clustering method based on unmasking, a...

Please sign up or login with your details

Forgot password? Click here to reset