Towards More Unified In-context Visual Understanding

arXiv:2312.02520v2 Announce Type: replace
Abstract: The rapid advancement of large language models (LLMs) has accelerated the emergence of in-context learning (ICL) as a cutting-edge approach in the natural language processing domain. Recently, ICL has been employed in visual understanding tasks, such as semantic segmentation and image captioning, yielding promising results. However, existing visual ICL framework can not enable producing content across multiple modalities, which limits their potential usage scenarios. To address this issue, we present a new ICL framework for …

abstract advancement arxiv captioning context cs.cv domain edge emergence however image in-context learning language language models language processing large language large language models llms natural natural language natural language processing processing results segmentation semantic tasks type understanding visual