An evaluation of large-scale methods for image instance and class discovery

TL;DR

This paper evaluates large-scale image discovery methods, highlighting the effectiveness of diffusion algorithms like Markov Clustering over traditional k-means, especially on extensive datasets with minimal human labeling effort.

Contribution

It demonstrates the advantages of diffusion-based clustering methods, particularly Markov Clustering, for large-scale image discovery tasks, outperforming traditional approaches.

Findings

Markov Clustering outperforms other methods in large-scale scenarios.

GPU implementation reduces discovery costs significantly.

Descriptor selection impacts object class discovery.

Abstract

This paper aims at discovering meaningful subsets of related images from large image collections without annotations. We search groups of images related at different levels of semantic, i.e., either instances or visual classes. While k-means is usually considered as the gold standard for this task, we evaluate and show the interest of diffusion methods that have been neglected by the state of the art, such as the Markov Clustering algorithm. We report results on the ImageNet and the Paris500k instance dataset, both enlarged with images from YFCC100M. We evaluate our methods with a labelling cost that reflects how much effort a human would require to correct the generated clusters. Our analysis highlights several properties. First, when powered with an efficient GPU implementation, the cost of the discovery process is small compared to computing the image descriptors, even for collections as large as 100 million images. Second, we show that descriptions selected for instance search improve the discovery of object classes. Third, the Markov Clustering technique consistently outperforms other methods; to our knowledge it has never been considered in this large scale scenario.