PulseAugur
实时 14:34:41
English(EN) ToolFG: Towards Well-Grounded Fine-Grained Image Classification

ToolFG框架使用MLLM和工具进行图像分类

研究人员推出ToolFG,一个专为细粒度图像分类设计的新型框架,该框架集成了多模态大语言模型(MLLMs)和外部工具。这种方法允许MLLMs自主使用工具与图像交互并收集可验证的视觉线索,从而提高了区分高度相似类别之间的可靠性。该框架采用MCTS引导的知识蒸馏机制和模型-工具协同演进过程,以优化工具和模型在专业FGIC任务中的工具使用策略。 AI

影响 通过将MLLM与外部工具集成,为细粒度图像分类引入了一种新方法,有望提高区分相似视觉类别的准确性。

排序理由 该集群包含一篇描述新框架和方法的学术论文。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · Yu Xue, Haoxuan Qu, Zhuoling Li, Yihang Lou, Yan Bai, Hossein Rahmani, Jun Liu ·

    ToolFG: Towards Well-Grounded Fine-Grained Image Classification

    arXiv:2606.02518v1 Announce Type: new Abstract: Fine-grained image classification (FGIC) has broad applications and has attracted significant research attention. In this paper, we explore a novel paradigm for solving FGIC by proposing \textbf{ToolFG}, the first tool-integrated ML…

  2. arXiv cs.CV TIER_1 English(EN) · Jun Liu ·

    ToolFG: Towards Well-Grounded Fine-Grained Image Classification

    Fine-grained image classification (FGIC) has broad applications and has attracted significant research attention. In this paper, we explore a novel paradigm for solving FGIC by proposing \textbf{ToolFG}, the first tool-integrated MLLM-based framework tailored to FGIC. ToolFG enab…