Unsupervised Image Segmentation using Mutual Mean-Teaching
This work addresses the instability of unsupervised image segmentation for computer vision researchers by providing a more stable training approach.
This paper proposes an unsupervised image segmentation model using a Mutual Mean-Teaching (MMT) framework to achieve more stable results. It also introduces a label alignment algorithm based on the Hungarian algorithm to match cluster labels between models. The model can segment various image types and outperforms existing methods.
Unsupervised image segmentation aims at assigning the pixels with similar feature into a same cluster without annotation, which is an important task in computer vision. Due to lack of prior knowledge, most of existing model usually need to be trained several times to obtain suitable results. To address this problem, we propose an unsupervised image segmentation model based on the Mutual Mean-Teaching (MMT) framework to produce more stable results. In addition, since the labels of pixels from two model are not matched, a label alignment algorithm based on the Hungarian algorithm is proposed to match the cluster labels. Experimental results demonstrate that the proposed model is able to segment various types of images and achieves better performance than the existing methods.