Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning

• URL: http://arxiv.org/abs/2602.07605v2
• Date: Tue, 10 Feb 2026 04:29:03 GMT
• Title: Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning
• Authors: Hulingxiao He, Zijun Geng, Yuxin Peng,
• Abstract summary: Fine-R1 is an R1-style MLLM tailored for Fine-Grained Visual Recognition.<n>With only 4-shot training, Fine-R1 outperforms existing general MLLMs, reasoning MLLMs, and even contrastive CLIP models.
• Score: 47.868429337792314
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Any entity in the visual world can be hierarchically grouped based on shared characteristics and mapped to fine-grained sub-categories. While Multi-modal Large Language Models (MLLMs) achieve strong performance on coarse-grained visual tasks, they often struggle with Fine-Grained Visual Recognition (FGVR). Adapting general-purpose MLLMs to FGVR typically requires large amounts of annotated data, which is costly to obtain, leaving a substantial performance gap compared to contrastive CLIP models dedicated for discriminative tasks. Moreover, MLLMs tend to overfit to seen sub-categories and generalize poorly to unseen ones. To address these challenges, we propose Fine-R1, an MLLM tailored for FGVR through an R1-style training framework: (1) Chain-of-Thought Supervised Fine-tuning, where we construct a high-quality FGVR CoT dataset with rationales of "visual analysis, candidate sub-categories, comparison, and prediction", transition the model into a strong open-world classifier; and (2) Triplet Augmented Policy Optimization, where Intra-class Augmentation mixes trajectories from anchor and positive images within the same category to improve robustness to intra-class variance, while Inter-class Augmentation maximizes the response distinction conditioned on images across sub-categories to enhance discriminative ability. With only 4-shot training, Fine-R1 outperforms existing general MLLMs, reasoning MLLMs, and even contrastive CLIP models in identifying both seen and unseen sub-categories, showing promise in working in knowledge-intensive domains where gathering expert annotations for all sub-categories is arduous. Code is available at https://github.com/PKU-ICST-MIPL/FineR1_ICLR2026.

Related papers

• Large Multimodal Models as General In-Context Classifiers [73.11242790834383]
  In this work, we argue that this answer overlooks an important capability of LMMs: in-context learning.<n>We benchmark state-of-the-art LMMs on diverse datasets for closed-world classification and find that, although their zero-shot performance is lower than CLIP's, LMMs with a few in-context examples can match or even surpass contrastive VLMs with cache-based adapters.<n>We extend this analysis to the open-world setting, where the generative nature of LMMs makes them more suitable for the task.
  arXiv  Detail & Related papers  (2026-02-26T17:08:18Z)
• Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models [31.34575955517015]
  Finedefics is an MLLM that enhances the model's FGVR capability by incorporating informative attribute descriptions of objects into the training phase.<n>We employ contrastive learning on object-attribute pairs and attribute-category pairs simultaneously and use examples from similar but incorrect categories as hard negatives.<n> Extensive evaluations across multiple popular FGVR datasets demonstrate that Finedefics outperforms existing MLLMs of comparable parameter sizes.
  arXiv  Detail & Related papers  (2025-01-25T08:52:43Z)
• Category-Adaptive Cross-Modal Semantic Refinement and Transfer for Open-Vocabulary Multi-Label Recognition [59.203152078315235]
  We propose a novel category-adaptive cross-modal semantic refinement and transfer (C$2$SRT) framework to explore the semantic correlation.<n>The proposed framework consists of two complementary modules, i.e., intra-category semantic refinement (ISR) module and inter-category semantic transfer (IST) module.<n>Experiments on OV-MLR benchmarks clearly demonstrate that the proposed C$2$SRT framework outperforms current state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2024-12-09T04:00:18Z)
• How to Make LLMs Strong Node Classifiers? [70.14063765424012]
  Language Models (LMs) are challenging the dominance of domain-specific models, such as Graph Neural Networks (GNNs) and Graph Transformers (GTs)<n>We propose a novel approach that empowers off-the-shelf LMs to achieve performance comparable to state-of-the-art (SOTA) GNNs on node classification tasks.
  arXiv  Detail & Related papers  (2024-10-03T08:27:54Z)
• RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition [78.97487780589574]
  Multimodal Large Language Models (MLLMs) excel at classifying fine-grained categories. This paper introduces a Retrieving And Ranking augmented method for MLLMs. Our proposed approach not only addresses the inherent limitations in fine-grained recognition but also preserves the model's comprehensive knowledge base.
  arXiv  Detail & Related papers  (2024-03-20T17:59:55Z)
• CLAMP: Contrastive LAnguage Model Prompt-tuning [89.96914454453791]
  We show that large language models can achieve good image classification performance when adapted this way. Our approach beats state-of-the-art mLLMs by 13% and slightly outperforms contrastive learning with a custom text model.
  arXiv  Detail & Related papers  (2023-12-04T05:13:59Z)
• LLMs as Visual Explainers: Advancing Image Classification with Evolving Visual Descriptions [13.546494268784757]
  We propose a framework that integrates large language models (LLMs) and vision-language models (VLMs) to find the optimal class descriptors. Our training-free approach develops an LLM-based agent with an evolutionary optimization strategy to iteratively refine class descriptors.
  arXiv  Detail & Related papers  (2023-11-20T16:37:45Z)
• CLIP Is Also a Good Teacher: A New Learning Framework for Inductive Zero-shot Semantic Segmentation [6.181169909576527]
  Generalized Zero-shot Semantic aims to segment both seen and unseen categories only under the supervision of the seen ones. Existing methods adopt the large-scale Vision Language Models (VLMs) which obtain outstanding zero-shot performance. We propose CLIP-ZSS (Zero-shot Semantic), a training framework that enables any image encoder designed for closed-set segmentation applied in zero-shot and open-vocabulary tasks.
  arXiv  Detail & Related papers  (2023-10-03T09:33:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.