EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation

arXiv:2403.01482v1 Announce Type: new
Abstract: Semantic segmentation has innately relied on extensive pixel-level labeled annotated data, leading to the emergence of unsupervised methodologies. Among them, leveraging self-supervised Vision Transformers for unsupervised semantic segmentation (USS) has been making steady progress with expressive deep features. Yet, for semantically segmenting images with complex objects, a predominant challenge remains: the lack of explicit object-level semantic encoding in patch-level features. This technical limitation often leads to inadequate segmentation of complex objects with diverse structures. To …

abstract aggregation annotated data arxiv cs.cv data emergence features images making objects pixel progress segmentation semantic them transformers type unsupervised vision vision transformers