Toward Interactive Regional Understanding in Vision-Large Language Models

arXiv:2403.18260v1 Announce Type: new
Abstract: Recent Vision-Language Pre-training (VLP) models have demonstrated significant advancements. Nevertheless, these models heavily rely on image-text pairs that capture only coarse and global information of an image, leading to a limitation in their regional understanding ability. In this work, we introduce \textbf{RegionVLM}, equipped with explicit regional modeling capabilities, allowing them to understand user-indicated image regions. To achieve this, we design a simple yet innovative architecture, requiring no modifications to the model architecture or objective function. …

abstract arxiv cs.cl cs.cv global image information interactive language language models large language large language models modeling pre-training regional text training type understanding vision work