AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Models

• URL: http://arxiv.org/abs/2507.02664v2
• Date: Mon, 07 Jul 2025 08:00:38 GMT
• Title: AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Models
• Authors: Ziyin Zhou, Yunpeng Luo, Yuanchen Wu, Ke Sun, Jiayi Ji, Ke Yan, Shouhong Ding, Xiaoshuai Sun, Yunsheng Wu, Rongrong Ji,
• Abstract summary: The rapid development of AI-generated content (AIGC) has led to the misuse of AI-generated images (AIGI) in spreading misinformation.<n>We introduce a large-scale and comprehensive dataset, Holmes-Set, which includes an instruction-tuning dataset with explanations on whether images are AI-generated.<n>Our work introduces an efficient data annotation method called the Multi-Expert Jury, enhancing data generation through structured MLLM explanations and quality control.<n>In addition, we propose Holmes Pipeline, a meticulously designed three-stage training framework comprising visual expert pre-training, supervised fine-tuning, and direct preference optimization
• Score: 78.08374249341514
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid development of AI-generated content (AIGC) technology has led to the misuse of highly realistic AI-generated images (AIGI) in spreading misinformation, posing a threat to public information security. Although existing AIGI detection techniques are generally effective, they face two issues: 1) a lack of human-verifiable explanations, and 2) a lack of generalization in the latest generation technology. To address these issues, we introduce a large-scale and comprehensive dataset, Holmes-Set, which includes the Holmes-SFTSet, an instruction-tuning dataset with explanations on whether images are AI-generated, and the Holmes-DPOSet, a human-aligned preference dataset. Our work introduces an efficient data annotation method called the Multi-Expert Jury, enhancing data generation through structured MLLM explanations and quality control via cross-model evaluation, expert defect filtering, and human preference modification. In addition, we propose Holmes Pipeline, a meticulously designed three-stage training framework comprising visual expert pre-training, supervised fine-tuning, and direct preference optimization. Holmes Pipeline adapts multimodal large language models (MLLMs) for AIGI detection while generating human-verifiable and human-aligned explanations, ultimately yielding our model AIGI-Holmes. During the inference stage, we introduce a collaborative decoding strategy that integrates the model perception of the visual expert with the semantic reasoning of MLLMs, further enhancing the generalization capabilities. Extensive experiments on three benchmarks validate the effectiveness of our AIGI-Holmes.

Related papers

• ForenX: Towards Explainable AI-Generated Image Detection with Multimodal Large Language Models [82.04858317800097]
  We present ForenX, a novel method that not only identifies the authenticity of images but also provides explanations that resonate with human thoughts.<n>ForenX employs the powerful multimodal large language models (MLLMs) to analyze and interpret forensic cues.<n>We introduce ForgReason, a dataset dedicated to descriptions of forgery evidences in AI-generated images.
  arXiv  Detail & Related papers  (2025-08-02T15:21:26Z)
• Quality Assessment and Distortion-aware Saliency Prediction for AI-Generated Omnidirectional Images [70.49595920462579]
  This work studies the quality assessment and distortion-aware saliency prediction problems for AIGODIs.<n>We propose two models with shared encoders based on the BLIP-2 model to evaluate the human visual experience and predict distortion-aware saliency for AI-generated omnidirectional images.
  arXiv  Detail & Related papers  (2025-06-27T05:36:04Z)
• Interpretable and Reliable Detection of AI-Generated Images via Grounded Reasoning in MLLMs [43.08776932101172]
  We build a dataset of AI-generated images annotated with bounding boxes and descriptive captions.<n>We then finetune MLLMs through a multi-stage optimization strategy.<n>The resulting model achieves superior performance in both detecting AI-generated images and localizing visual flaws.
  arXiv  Detail & Related papers  (2025-06-08T08:47:44Z)
• OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoning [76.90511414963265]
  We introduce OmniAD, a framework that unifies anomaly detection and understanding for fine-grained analysis.<n>Visual reasoning provides detailed inspection by leveraging Text-as-Mask.<n>Visual Guided Textual Reasoning conducts comprehensive analysis by integrating visual perception.
  arXiv  Detail & Related papers  (2025-05-28T07:02:15Z)
• A Comprehensive Framework for Semantic Similarity Analysis of Human and AI-Generated Text Using Transformer Architectures and Ensemble Techniques [40.704014941800594]
  Traditional methods fail to capture nuanced semantic differences between human and machine-generated content.<n>We propose a novel approach that combines a pre-trained DeBERTa-v3-large model, Bi-directional LSTMs, and linear attention pooling to capture both local and global semantic patterns.<n> Experimental results show that this approach works better than traditional methods, proving its usefulness for AI-generated text detection and other text comparison tasks.
  arXiv  Detail & Related papers  (2025-01-24T07:07:37Z)
• Generative Artificial Intelligence Meets Synthetic Aperture Radar: A Survey [49.29751866761522]
  This paper aims to investigate the intersection of GenAI and SAR. First, we illustrate the common data generation-based applications in SAR field. Then, an overview of the latest GenAI models is systematically reviewed. Finally, the corresponding applications in SAR domain are also included.
  arXiv  Detail & Related papers  (2024-11-05T03:06:00Z)
• XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach [2.0209172586699173]
  This paper introduces a novel XAI-integrated Visual Quality Inspection framework. Our framework incorporates XAI and the Large Vision Language Model to deliver human-centered interpretability. This approach paves the way for the broader adoption of reliable and interpretable AI tools in critical industrial applications.
  arXiv  Detail & Related papers  (2024-07-16T14:30:24Z)
• LAMBO: Large AI Model Empowered Edge Intelligence [71.56135386994119]
  Next-generation edge intelligence is anticipated to benefit various applications via offloading techniques. Traditional offloading architectures face several issues, including heterogeneous constraints, partial perception, uncertain generalization, and lack of tractability. We propose a Large AI Model-Based Offloading (LAMBO) framework with over one billion parameters for solving these problems.
  arXiv  Detail & Related papers  (2023-08-29T07:25:42Z)
• IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing [88.35145788575348]
  Image anomaly detection (IAD) is an emerging and vital computer vision task in industrial manufacturing. The lack of a uniform IM benchmark is hindering the development and usage of IAD methods in real-world applications. We construct a comprehensive image anomaly detection benchmark (IM-IAD), which includes 19 algorithms on seven major datasets.
  arXiv  Detail & Related papers  (2023-01-31T01:24:45Z)

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.