Mixed-Query Transformer: A Unified Image Segmentation Architecture

arXiv:2404.04469v1 Announce Type: new
Abstract: Existing unified image segmentation models either employ a unified architecture across multiple tasks but use separate weights tailored to each dataset, or apply a single set of weights to multiple datasets but are limited to a single task. In this paper, we introduce the Mixed-Query Transformer (MQ-Former), a unified architecture for multi-task and multi-dataset image segmentation using a single set of weights. To enable this, we propose a mixed query strategy, which can effectively and …

abstract apply architecture arxiv cs.cv dataset datasets image mixed multiple paper query segmentation set tasks transformer type unified architecture