GMAIR: Unsupervised Object Detection Based on Spatial Attention and Gaussian Mixture

TL;DR

GMAIR is an unsupervised deep generative model that simultaneously locates and clusters objects in scenes, emphasizing the importance of learning object attributes alongside positions, and demonstrating competitive results on benchmark datasets.

Contribution

This paper introduces GMAIR, a novel framework combining spatial attention and Gaussian mixture modeling for unsupervised object detection and clustering.

Findings

GMAIR effectively locates objects in scenes.

GMAIR successfully clusters objects without supervision.

The model achieves competitive results on MultiMNIST and Fruit2D datasets.

Abstract

Recent studies on unsupervised object detection based on spatial attention have achieved promising results. Models, such as AIR and SPAIR, output "what" and "where" latent variables that represent the attributes and locations of objects in a scene, respectively. Most of the previous studies concentrate on the "where" localization performance; however, we claim that acquiring "what" object attributes is also essential for representation learning. This paper presents a framework, GMAIR, for unsupervised object detection. It incorporates spatial attention and a Gaussian mixture in a unified deep generative model. GMAIR can locate objects in a scene and simultaneously cluster them without supervision. Furthermore, we analyze the "what" latent variables and clustering process. Finally, we evaluate our model on MultiMNIST and Fruit2D datasets and show that GMAIR achieves competitive results on localization and clustering compared to state-of-the-art methods.