GROUNDHOG: Grounding Large Language Models to Holistic Segmentation

arXiv:2402.16846v2 Announce Type: replace-cross
Abstract: Most multimodal large language models (MLLMs) learn language-to-object grounding through causal language modeling where grounded objects are captured by bounding boxes as sequences of location tokens. This paradigm lacks pixel-level representations that are important for fine-grained visual understanding and diagnosis. In this work, we introduce GROUNDHOG, an MLLM developed by grounding Large Language Models to holistic segmentation. GROUNDHOG incorporates a masked feature extractor and converts extracted features into visual entity tokens for the MLLM backbone, …

abstract arxiv causal cs.ai cs.cl cs.cv diagnosis fine-grained language language models large language large language models learn location mllms modeling multimodal object objects paradigm pixel segmentation through tokens type understanding visual work