GMAIR: Unsupervised Object Detection Based on Spatial Attention and Gaussian Mixture
This work addresses the problem of unsupervised object detection and clustering for computer vision researchers, representing an incremental improvement by focusing on 'what' attributes alongside localization.
The paper tackles unsupervised object detection by proposing GMAIR, a framework that integrates spatial attention and Gaussian mixture in a deep generative model to locate and cluster objects without supervision, achieving competitive results on MultiMNIST and Fruit2D datasets.
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.