Two Tricks to Improve Unsupervised Segmentation Learning

arXiv:2404.03392v1 Announce Type: new
Abstract: We present two practical improvement techniques for unsupervised segmentation learning. These techniques address limitations in the resolution and accuracy of predicted segmentation maps of recent state-of-the-art methods. Firstly, we leverage image post-processing techniques such as guided filtering to refine the output masks, improving accuracy while avoiding substantial computational costs. Secondly, we introduce a multi-scale consistency criterion, based on a teacher-student training scheme. This criterion matches segmentation masks predicted from regions of the input image extracted …

abstract accuracy art arxiv computational cs.cv filtering image improvement improving limitations maps masks post-processing practical processing refine resolution segmentation state tricks type unsupervised