Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment

• URL: http://arxiv.org/abs/2506.05384v2
• Date: Thu, 12 Jun 2025 16:38:10 GMT
• Title: Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment
• Authors: Zhuoxuan Cai, Jian Zhang, Xinbin Yuan, Peng-Tao Jiang, Wenxiang Chen, Bowen Tang, Lujian Yao, Qiyuan Wang, Jinwen Chen, Bo Li,
• Abstract summary: multimodal large language models (MLLMs) can proficiently evaluate visual quality through interpretable assessments.<n>We propose a unified two-stage training framework comprising a cold-start stage and a reinforcement learning-based fine-tuning stage.<n>We designate the models derived from these two stages as Q-Ponder-CI and Q-Ponder.
• Score: 10.701522670464463
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent studies demonstrate that multimodal large language models (MLLMs) can proficiently evaluate visual quality through interpretable assessments. However, existing approaches typically treat quality scoring and reasoning descriptions as separate tasks with disjoint optimization objectives, leading to a trade-off: models adept at quality reasoning descriptions struggle with precise score regression, while score-focused models lack interpretability. This limitation hinders the full potential of MLLMs in visual quality assessment, where accuracy and interpretability should be mutually reinforcing. To address this, we propose a unified two-stage training framework comprising a cold-start stage and a reinforcement learning-based fine-tuning stage. Specifically, in the first stage, we distill high-quality data from a teacher model through expert-designed prompts, initializing reasoning capabilities via cross-entropy loss supervision. In the second stage, we introduce a novel reward with Group Relative Policy Optimization (GRPO) to jointly optimize scoring accuracy and reasoning consistency. We designate the models derived from these two stages as Q-Ponder-CI and Q-Ponder. Extensive experiments show that Q-Ponder achieves state-of-the-art (SOTA) performance on quality score regression benchmarks, delivering up to 6.5% higher SRCC on cross-domain datasets. Furthermore, Q-Ponder significantly outperforms description-based SOTA models, including its teacher model Qwen-2.5-VL-72B, particularly in description accuracy and reasonableness, demonstrating the generalization potential over diverse tasks.

Related papers

• Refine-IQA: Multi-Stage Reinforcement Finetuning for Perceptual Image Quality Assessment [22.184690568393126]
  Reinforcement fine-tuning (RFT) is a proliferating paradigm for LMM training.<n>We propose a multi-stage RFT IQA framework (-IQA)<n>The resulting Refine-IQA Series Models achieve outstanding performance on both perception and scoring tasks.
  arXiv  Detail & Related papers  (2025-08-04T22:46:10Z)
• T2I-Eval-R1: Reinforcement Learning-Driven Reasoning for Interpretable Text-to-Image Evaluation [60.620408007636016]
  We propose T2I-Eval-R1, a novel reinforcement learning framework that trains open-source MLLMs using only coarse-grained quality scores.<n>Our approach integrates Group Relative Policy Optimization into the instruction-tuning process, enabling models to generate both scalar scores and interpretable reasoning chains.
  arXiv  Detail & Related papers  (2025-05-23T13:44:59Z)
• Breaking Annotation Barriers: Generalized Video Quality Assessment via Ranking-based Self-Supervision [49.46606936180063]
  Video quality assessment (VQA) is essential for quantifying quality in various video processing systems.<n>We introduce a self-supervised learning framework for VQA to learn quality assessment capabilities from large-scale, unlabeled web videos.<n>By training on a dataset $10times$ larger than the existing VQA benchmarks, our model achieves zero-shot performance.
  arXiv  Detail & Related papers  (2025-05-06T15:29:32Z)
• Teaching LMMs for Image Quality Scoring and Interpreting [71.1335005098584]
  We propose Q-SiT (Quality Scoring and Interpreting joint Teaching), a unified framework that enables image quality scoring and interpreting simultaneously.<n>Q-SiT is the first model capable of simultaneously performing image quality scoring and interpreting tasks, along with its lightweight variant, Q-SiT-mini.<n> Experimental results demonstrate that Q-SiT achieves strong performance in both tasks with superior generalization IQA abilities.
  arXiv  Detail & Related papers  (2025-03-12T09:39:33Z)
• Multi-Modal Prompt Learning on Blind Image Quality Assessment [65.0676908930946]
  Image Quality Assessment (IQA) models benefit significantly from semantic information, which allows them to treat different types of objects distinctly. Traditional methods, hindered by a lack of sufficiently annotated data, have employed the CLIP image-text pretraining model as their backbone to gain semantic awareness. Recent approaches have attempted to address this mismatch using prompt technology, but these solutions have shortcomings. This paper introduces an innovative multi-modal prompt-based methodology for IQA.
  arXiv  Detail & Related papers  (2024-04-23T11:45:32Z)
• BloomVQA: Assessing Hierarchical Multi-modal Comprehension [18.21961616174999]
  We collect multiple-choice samples based on picture stories that reflect different levels of comprehension. Our data maps to a novel hierarchical graph representation which enables automatic data augmentation and novel measures characterizing model consistency. In comparison to earlier models, GPT-4V demonstrates improved accuracy over all comprehension levels and shows a tendency of bypassing visual inputs especially for higher-level tasks.
  arXiv  Detail & Related papers  (2023-12-20T02:22:49Z)
• Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models [61.28463542324576]
  Vision-language models (VLMs) have recently demonstrated strong efficacy as visual assistants that can generate human-like outputs. We evaluate existing state-of-the-art VLMs and find that even the best-performing model is unable to demonstrate strong visual reasoning capabilities and consistency. We propose a two-stage training framework aimed at improving both the reasoning performance and consistency of VLMs.
  arXiv  Detail & Related papers  (2023-09-08T17:49:44Z)
• Counterfactual Samples Synthesizing for Robust Visual Question Answering [104.72828511083519]
  We propose a model-agnostic Counterfactual Samples Synthesizing (CSS) training scheme. CSS generates numerous counterfactual training samples by masking critical objects in images or words in questions. We achieve a record-breaking performance of 58.95% on VQA-CP v2, with 6.5% gains.
  arXiv  Detail & Related papers  (2020-03-14T08:34:31Z)

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.