Lost in Space: Probing Fine-grained Spatial Understanding in Vision and Language Resamplers

arXiv:2404.13594v1 Announce Type: new
Abstract: An effective method for combining frozen large language models (LLM) and visual encoders involves a resampler module that creates a `visual prompt' which is provided to the LLM, along with the textual prompt. While this approach has enabled impressive performance across many coarse-grained tasks like image captioning and visual question answering, more fine-grained tasks that require spatial understanding have not been thoroughly examined. In this paper, we use \textit{diagnostic classifiers} to measure the extent to …

abstract arxiv cs.ai cs.cv fine-grained language language models large language large language models llm lost performance prompt space spatial textual type understanding vision visual