Toward unsupervised, multi-object discovery in large-scale image collections

TL;DR

This paper introduces an unsupervised method for discovering multiple objects in large-scale image collections by leveraging a novel saliency-based proposal algorithm, hierarchical regularization, and a two-stage selection process, significantly advancing the state of the art.

Contribution

It presents a new unsupervised object discovery approach that improves proposal quality, exploits hierarchical proposal structures, and enables large-scale multi-object discovery in extensive image datasets.

Findings

Outperforms existing methods on standard benchmarks.

Enables discovery of multiple objects per image in large datasets.

Achieves over five times the scale of previous unsupervised methods.

Abstract

This paper addresses the problem of discovering the objects present in a collection of images without any supervision. We build on the optimization approach of Vo et al. (CVPR'19) with several key novelties: (1) We propose a novel saliency-based region proposal algorithm that achieves significantly higher overlap with ground-truth objects than other competitive methods. This procedure leverages off-the-shelf CNN features trained on classification tasks without any bounding box information, but is otherwise unsupervised. (2) We exploit the inherent hierarchical structure of proposals as an effective regularizer for the approach to object discovery of Vo et al., boosting its performance to significantly improve over the state of the art on several standard benchmarks. (3) We adopt a two-stage strategy to select promising proposals using small random sets of images before using the whole image collection to discover the objects it depicts, allowing us to tackle, for the first time (to the best of our knowledge), the discovery of multiple objects in each one of the pictures making up datasets with up to 20,000 images, an over five-fold increase compared to existing methods, and a first step toward true large-scale unsupervised image interpretation.