UC-VLM: Consistency-Driven Learning for AI-Generated Image Detection with Vision-Language Large Models

• URL: http://arxiv.org/abs/2608.15238v1
• Date: Sat, 15 Aug 2026 13:53:59 GMT
• Title: UC-VLM: Consistency-Driven Learning for AI-Generated Image Detection with Vision-Language Large Models
• Abstract summary: UC-VLM is a unified multi-stage framework for AIGI detection that relies solely on binary supervision.<n>It consistently reuses the same authenticity labels for visual adaptation and label-conditioned text generation.<n>Experiments show that UC-VLM achieves 96.1% average accuracy on GenImage, exceeding the strongest prior result by 4.6%.
• Score: 34.80872382508184
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-Language Large Models (VLLMs) are promising for AI-generated image (AIGI) detection because they can produce both a prediction and a natural-language output. However, most existing VLLM-based detectors primarily fine-tune the language side while giving limited attention to low-level visual forensic cues. They also often depend on manually crafted prompts or human-annotated rationales, which limits scalability.We present UC-VLM, a unified multi-stage framework for AIGI detection that relies solely on binary supervision. UC-VLM first identifies effective instruction variants automatically. It then reuses the same binary label within a multi-stage training framework: (i) a visual discrimination objective that strengthens sensitivity to non-semantic forensic cues, and (ii) a label-conditioned generation objective that uses the binary label to supervise textual outputs. This design turns weak binary supervision into a shared supervision signal for both the visual pathway and the language output. Our key novelty is a unified multi-stage binary-supervised framework that consistently reuses the same authenticity labels for visual adaptation and label-conditioned text generation, while leveraging automatically optimized instructions to reduce prompt sensitivity without requiring human-written rationales or hand-crafted prompts.Experiments show that UC-VLM achieves 96.1% average accuracy on GenImage, exceeding the strongest prior result by 4.6%, and obtains 69.6% / 77.9% accuracy on Chameleon under ProGAN / SDV1.4 training, surpassing the best baseline by 11.2% / 15.3%, respectively.

Related papers

• Decoupling Semantics from Distortions: Multi-Scale Two-Stream Vision-Language Alignment for AI-Generated Image Quality Assessment [0.4790056963046066]
  MST-CLIPIQA is a multi-scale two-stream framework that achieves hierarchical vision-language alignment through explicit representational decoupling.<n>Our architecture leverages dual CLIP encoders with complementary patch granularities, capturing global semantic coherence.<n>Experiments establish new state-of-the-art results, achieving average improvements of 1.11 percent SRCC on quality and 2.35 percent SRCC on text-image correspondence prediction.
  arXiv  Detail & Related papers  (2026-06-15T14:40:30Z)
• [CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation [20.637119409165418]
  PIAA formulates prediction as Patch-level Inference followed by Adaptive Aggregation.<n>We introduce an adaptive aggregation module that consolidates patch-level scores into the final multi-label prediction.<n>Experiments show that our method achieves strong improvements with minimal extra computation.
  arXiv  Detail & Related papers  (2026-05-25T13:19:12Z)
• Reasoning-Aware AIGC Detection via Alignment and Reinforcement [55.09684020007737]
  REVEAL is a framework that generates interpretable reasoning chains before classification.<n>It achieves state-of-the-art performance across multiple benchmarks.
  arXiv  Detail & Related papers  (2026-04-21T07:29:55Z)
• AEyeDE: An Attention-Based Attribution Framework for AI-Generated Text Detection [1.373282478189168]
  We propose textscAEyeDE, an attribution-driven approach to human-AI authorship detection.<n>We show that attention-based attribution maps provide a complementary and interpretable signal for AI-generated text detection.
  arXiv  Detail & Related papers  (2026-04-13T19:30:40Z)
• Unifying Heterogeneous Multi-Modal Remote Sensing Detection Via Language-Pivoted Pretraining [59.2578488860426]
  Heterogeneous multi-modal remote sensing object detection aims to accurately detect objects from diverse sensors.<n>Existing approaches largely adopt a late alignment paradigm, in which modality alignment and task-specific optimization are entangled during downstream fine-tuning.<n>We propose BabelRS, a unified language-pivoted pretraining framework that explicitly decouples modality alignment from downstream task learning.
  arXiv  Detail & Related papers  (2026-03-02T11:38:12Z)
• SSVP: Synergistic Semantic-Visual Prompting for Industrial Zero-Shot Anomaly Detection [55.54007781679915]
  We propose Synergistic Semantic-Visual Prompting (SSVP), that efficiently fuses diverse visual encodings to elevate model's fine-grained perception.<n>SSVP achieves state-of-the-art performance with 93.0% Image-AUROC and 92.2% Pixel-AUROC on MVTec-AD, significantly outperforming existing zero-shot approaches.
  arXiv  Detail & Related papers  (2026-01-14T04:42:19Z)
• Task-Model Alignment: A Simple Path to Generalizable AI-Generated Image Detection [57.17054616831796]
  Vision Language Models (VLMs) are increasingly adopted for AI-generated images (AIGI) detection.<n>VLMs' underperformance is attributed to task-model misalignment.<n>In this paper, we formalize AIGI detection as two complementary tasks--semantic consistency checking and pixel-artifact detection.
  arXiv  Detail & Related papers  (2025-12-07T09:19:00Z)
• Text-Visual Semantic Constrained AI-Generated Image Quality Assessment [47.575342788480505]
  We propose a unified framework to enhance the comprehensive evaluation of both text-image consistency and perceptual distortion in AI-generated images.<n>Our approach integrates key capabilities from multiple models and tackles the aforementioned challenges by introducing two core modules.<n>Tests conducted on multiple benchmark datasets demonstrate that SC-AGIQA outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-07-14T16:21:05Z)
• Vision-Language Consistency Guided Multi-modal Prompt Learning for Blind AI Generated Image Quality Assessment [57.07360640784803]
  We propose vision-language consistency guided multi-modal prompt learning for blind image quality assessment (AGIQA) Specifically, we introduce learnable textual and visual prompts in language and vision branches of Contrastive Language-Image Pre-training (CLIP) models. We design a text-to-image alignment quality prediction task, whose learned vision-language consistency knowledge is used to guide the optimization of the above multi-modal prompts.
  arXiv  Detail & Related papers  (2024-06-24T13:45:31Z)
• 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)
• Prefix Conditioning Unifies Language and Label Supervision [84.11127588805138]
  We show that dataset biases negatively affect pre-training by reducing the generalizability of learned representations. In experiments, we show that this simple technique improves the performance in zero-shot image recognition accuracy and robustness to the image-level distribution shift.
  arXiv  Detail & Related papers  (2022-06-02T16:12:26Z)

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.