Set-of-Mark提示法释放GPT-4V卓越的视觉 grounding 能力
Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
AI总结：
本研究提出Set-of-Mark（SoM）视觉提示法，借助SEEM/SAM等分割模型为图像添加多粒度标记，赋能GPT-4V实现更强的视觉定位能力，零样本下在RefCOCOg上超越全微调的SOTA模型。
摘要：
我们提出了一种新型视觉提示方法Set-of-Mark（SoM，标记集提示法），以释放GPT-4V等大型多模态模型（LMMs）的视觉定位能力。如图1（右）所示，我们采用现成的交互式分割模型（如SEEM/SAM）将图像划分为不同粒度的区域，并用一组标记（如字母数字、掩码、边界框）覆盖这些区域。以标记后的图像作为输入，GPT-4V能够回答需要视觉定位的问题。我们开展了全面的实证研究，在大量细粒度视觉与多模态任务上验证了SoM的有效性。例如，实验表明，采用SoM的GPT-4V在零样本设置下，在RefCOCOg数据集上的表现优于当前最优的全微调指代表达理解与分割模型。SoM提示的代码已公开于：https://github.com/microsoft/SoM。
英文摘要：
We present Set-of-Mark (SoM), a new visual prompting method, to unleash the visual grounding abilities of large multimodal models (LMMs), such as GPT-4V. As illustrated in Fig. 1 (right), we employ off-the-shelf interactive segmentation models, such as SEEM/SAM, to partition an image into regions at different levels of granularity, and overlay these regions with a set of marks e.g., alphanumerics, masks, boxes. Using the marked image as input, GPT-4V can answer the questions that require visual grounding. We perform a comprehensive empirical study to validate the effectiveness of SoM on a wide range of fine-grained vision and multimodal tasks. For example, our experiments show that GPT-4V with SoM in zero-shot setting outperforms the state-of-the-art fully-finetuned referring expression comprehension and segmentation model on RefCOCOg. Code for SoM prompting is made public at: https://github.com/microsoft/SoM.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
