{"slug": "agidefect-4k-a-richly-annotated-dataset-for-ai-generated-image-defect-detection", "title": "AGIDefect-4K: A Richly Annotated Dataset for AI-Generated Image Defect Detection, Localization and Explanation", "summary": "Researchers released AGIDefect-4K, a dataset of 4,000 AI-generated images from 15 generative models with hierarchical annotations for defect detection, segmentation, explanation, and quality scoring, and introduced AGIDA, a baseline framework using multimodal large language models for joint defect analysis. Benchmarking shows AGI defect understanding remains challenging, highlighting the dataset's value for improving AI image reliability.", "body_md": "arXiv:2608.20713v1 Announce Type: new\nAbstract: Generative AI can now produce highly realistic images, yet current models still exhibit subtle but critical defects that undermine their reliability. While existing AI-generated image (AGI) evaluation benchmarks have made notable progress, comprehensive AGI defect diagnosis remains underexplored. To bridge this gap, we introduce AGIDefect-4K, a richly annotated dataset of 4,000 images from 15 state-of-the-art generative models spanning both open-source and closed-source systems. AGIDefect-4K features hierarchical defect annotations: (1) detection labels identifying whether defects exist, (2) pixel-level segmentation masks localizing defective regions, and (3) detailed textual explanations characterizing defect types and their perceptual impact. Each image is further annotated with an overall quality score. Building on this, we present AGIDA (AGI Defect Assistant), a baseline framework leveraging Multimodal Large Language Models (MLLMs) for joint defect detection, localization, explanation, and quality prediction. Comprehensive benchmarking on AGIDefect-4K reveals that AGI defect understanding remains challenging, underscoring the value of this dataset. The dataset is publicly available at https://github.com/sxfly99/AGIDefect-4K.", "url": "https://wpnews.pro/news/agidefect-4k-a-richly-annotated-dataset-for-ai-generated-image-defect-detection", "canonical_source": "https://arxiv.org/abs/2608.20713", "published_at": "2026-08-24 04:00:00+00:00", "updated_at": "2026-08-24 04:16:59.892166+00:00", "lang": "en", "topics": ["artificial-intelligence", "generative-ai", "computer-vision", "ai-research", "ai-tools"], "entities": ["AGIDefect-4K", "AGIDA", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/agidefect-4k-a-richly-annotated-dataset-for-ai-generated-image-defect-detection", "markdown": "https://wpnews.pro/news/agidefect-4k-a-richly-annotated-dataset-for-ai-generated-image-defect-detection.md", "text": "https://wpnews.pro/news/agidefect-4k-a-richly-annotated-dataset-for-ai-generated-image-defect-detection.txt", "jsonld": "https://wpnews.pro/news/agidefect-4k-a-richly-annotated-dataset-for-ai-generated-image-defect-detection.jsonld"}}