Cluster-based 3D reconstruction of aerial video

Sawyer, Scott M.; Ni, Karl; Bliss, Nadya

doi:10.1109/hpec.2012.6408681

Cited by 4 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image Clustering is a fundamental, challenging and widely studied problem in machine learning [3]- [8]. with variety of applications in image retrieval [9], fast 3D reconstructions [10] [11] [12] etc. Some classical examples are K-means [13], Gaussian Mixture Models [14] and Spectral clustering [6] which are promising, but require a robust feature representation for good clustering.…”

Section: Introductionmentioning

confidence: 99%

Variational Clustering: Leveraging Variational Autoencoders for Image Clustering

Prasad¹,

Das²,

Bhowmick³

2020

Preprint

View full text Add to dashboard Cite

Recent advances in deep learning have shown their ability to learn strong feature representations for images. The task of image clustering naturally requires good feature representations to capture the distribution of the data and subsequently differentiate data points from one another. Often these two aspects are dealt with independently and thus traditional feature learning alone does not suffice in partitioning the data meaningfully. Variational Autoencoders (VAEs) naturally lend themselves to learning data distributions in a latent space. Since we wish to efficiently discriminate between different clusters in the data, we propose a method based on VAEs where we use a Gaussian Mixture prior to help cluster the images accurately. We jointly learn the parameters of both the prior and the posterior distributions. Our method represents a true Gaussian Mixture VAE. This way, our method simultaneously learns a prior that captures the latent distribution of the images and a posterior to help discriminate well between data points. We also propose a novel reparametrization of the latent space consisting of a mixture of discrete and continuous variables. One key takeaway is that our method generalizes better across different datasets without using any pre-training or learnt models, unlike existing methods, allowing it to be trained from scratch in an end-to-end manner. We verify our efficacy and generalizability experimentally by achieving state-of-the-art results among unsupervised methods on a variety of datasets. To the best of our knowledge, we are the first to pursue image clustering using VAEs in a purely unsupervised manner on real image datasets.

show abstract

Section: Introductionmentioning

confidence: 99%