超越标签的思考：基于推理增强LMM的无词表细粒度识别
Thinking Beyond Labels: Vocabulary-Free Fine-Grained Recognition using Reasoning-Augmented LMMs
利用推理增强的LMM自动生成并筛选细粒度类别名称，再实例化为轻量多模态分类器，为无词表细粒度识别提供了可复用的三阶段流程，并证明开源LMM在精心设计提示下可媲美闭源模型。
原文依据 we propose FiNDR (Fine-grained Name Discovery via Reasoning), the first reasoning-augmented LMM-based framework for vocabulary-free fine-grained recognition
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论无词表细粒度图像识别旨在区分元类别内视觉相似的类别，而不依赖固定的人工定义标签集。现有解决方案仍受限于使用庞大且僵硬的词表，或依赖带有脆弱启发式的复杂流程，其中错误会跨阶段传播。与此同时，近期具备显式或隐式推理能力的大型多模态模型（LMM）在理解视觉-语言数据、分解问题、检索潜在知识以及自我纠正方面的能力，暗示了一种更原则化且有效的替代方案。基于这些能力，我们提出FiNDR（通过推理的细粒度名称发现），这是首个基于推理增强LMM的无词表细粒度识别框架。该系统以三个自动化步骤运行：(i) 一个支持推理的LMM为每张图像生成描述性候选标签；(ii) 一个视觉语言模型对这些候选进行过滤和排序，形成连贯的类别集；(iii) 验证后的名称实例化一个轻量级多模态分类器，用于推理阶段。在流行的细粒度分类基准上的大量实验表明，在无词表设定下达到了最优性能，相对先前方法有高达18.8%的显著相对优势。值得注意的是，所提方法超越了利用预定义真实名称的零样本基线，挑战了人工整理词表定义性能上限的假设。消融实验进一步证实，先进的提示技术和内置推理机制显著提升了命名质量。此外，我们表明精心设计的提示能使开源LMM媲美专有模型。这些发现确立了推理增强LMM作为可扩展、全自动、开放世界细粒度视觉识别的有效基础。源代码及相关提示指南将发布。
英文原文摘要 2045 字符
Vocabulary-free fine-grained image recognition aims to distinguish visually similar categories within a meta-class without a fixed, human-defined label set. Existing solutions for this problem remain limited by either the usage of a large and rigid list of vocabularies or by the dependency on complex pipelines with fragile heuristics where errors propagate across stages. Meanwhile, the ability of recent large multi-modal models (LMMs) equipped with explicit or implicit reasoning to comprehend visual-language data, decompose problems, retrieve latent knowledge, and self-correct suggests a more principled and effective alternative. Building on these capabilities, we propose FiNDR (Fine-grained Name Discovery via Reasoning), the first reasoning-augmented LMM-based framework for vocabulary-free fine-grained recognition. The system oper- ates in three automated steps: (i) a reasoning-enabled LMM generates descriptive candidate labels for each image; (ii) a vision-language model filters and ranks these candidates to form a coherent class set; and (iii) the verified names instantiate a lightweight multi-modal classifier used at inference time. Extensive experiments on popular fine-grained classification benchmarks demonstrate state-of-the-art per- formance under the vocabulary-free setting, with a significant relative margin of up to 18.8% over previous ap- proaches. Remarkably, the proposed method surpasses zero-shot baselines that exploit pre-defined ground-truth names, challenging the assumption that human-curated vo- cabularies define an upper bound. Ablations further confirm that advanced prompting techniques and built-in rea- soning mechanisms significantly enhance naming quality. Additionally, we show that carefully engineered prompts enable open-source LMMs to match proprietary counter- parts. These findings establish reasoning-augmented LMMs as an effective foundation for scalable, fully automated, open-world fine-grained visual recognition. The source code and relevant prompting guidelines will be released.