LaSagnA: Language-based Segmentation Assistant for Complex Queries

arXiv:2404.08506v1 Announce Type: new
Abstract: Recent advancements have empowered Large Language Models for Vision (vLLMs) to generate detailed perceptual outcomes, including bounding boxes and masks. Nonetheless, there are two constraints that restrict the further application of these vLLMs: the incapability of handling multiple targets per query and the failure to identify the absence of query objects in the image. In this study, we acknowledge that the main cause of these problems is the insufficient complexity of training queries. Consequently, we …

arxiv assistant complex queries cs.cv language queries segmentation type