Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection

• URL: http://arxiv.org/abs/2605.14486v1
• Date: Thu, 14 May 2026 07:26:36 GMT
• Title: Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection
• Abstract summary: A common strategy is to employ reconstruction techniques, e.g., VAE and DDIM, which show remarkable results in diffusion-based methods.<n>We propose a GAN-based upsampling approach that mimics GAN-generated fake patterns while preserving content, size, and format alignment.<n>We first train domain-specific experts via LoRA adaptation on a frozen foundational model, then conduct decoupled fusion with a gating network to adaptively combine expert features.
• Score: 34.37666528689241
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As the misuse of AI-generated images grows, generalizable image detection techniques are urgently needed. Recent state-of-the-art (SOTA) methods adopt aligned training datasets to reduce content, size, and format biases, empowering models to capture robust forgery cues. A common strategy is to employ reconstruction techniques, e.g., VAE and DDIM, which show remarkable results in diffusion-based methods. However, such reconstruction-based approaches typically introduce limited and homogeneous artifacts, which cannot fully capture diverse generative patterns, such as GAN-based methods. To complement reconstruction-based fake images with aligned yet diverse artifact patterns, we propose a GAN-based upsampling approach that mimics GAN-generated fake patterns while preserving content, size, and format alignment. This naturally results in two aligned but distinct types of fake images. However, due to the domain shift between reconstruction-based and upsampling-based fake images, direct mixed training causes suboptimal results, where one domain disrupts feature learning of the other. Accordingly, we propose a Separate Expert Fusion (SEF) framework to extract complementary artifact information and reduce inter-domain interference. We first train domain-specific experts via LoRA adaptation on a frozen foundational model, then conduct decoupled fusion with a gating network to adaptively combine expert features while retaining their specialized knowledge. Rather than merely benefiting GAN-generated image detection, this design introduces diverse and complementary artifact patterns that enable SEF to learn a more robust decision boundary and improve generalization across broader generative methods. Extensive experiments demonstrate that our method yields strong results across 13 diverse benchmarks. Codes are released at: https://github.com/liyih/SEF_AIGC_detection.

Related papers

• R$^2$BD: A Reconstruction-Based Method for Generalizable and Efficient Detection of Fake Images [31.9904761238593]
  We propose a novel fake image detection framework, called R$2$BD, built upon two key designs.<n>Experiments on the benchmark from 10 public datasets demonstrate that R$2$BD is over 22$times$ faster than existing reconstruction-based methods.<n>In cross-dataset evaluations, it outperforms state-of-the-art methods by an average of 13.87%.
  arXiv  Detail & Related papers  (2026-01-11T02:31:51Z)
• Detecting Generated Images by Fitting Natural Image Distributions [75.31113784234877]
  We propose a novel framework that exploits geometric differences between the data manifold of natural and generated images.<n>We employ a pair of functions engineered to yield consistent outputs for natural images but divergent outputs for generated ones.<n>An image is identified as generated if a transformation along its data manifold induces a significant change in the loss value of a self-supervised model pre-trained on natural images.
  arXiv  Detail & Related papers  (2025-11-03T07:20:38Z)
• Prompt-Free Conditional Diffusion for Multi-object Image Augmentation [45.92182911052815]
  We propose a prompt-free conditional diffusion framework for multi-object image augmentation.<n>Specifically, we introduce a local-global semantic fusion strategy to extract semantics from images to replace text.<n>We also design a reward model based counting loss to assist the traditional reconstruction loss for model training.
  arXiv  Detail & Related papers  (2025-07-08T16:27:48Z)
• GenMix: Effective Data Augmentation with Generative Diffusion Model Image Editing [60.101097709212716]
  This paper introduces GenMix, a generalizable prompt-guided generative data augmentation approach.<n>Our technique leverages image editing to generate augmented images based on custom conditional prompts.<n>Our approach mitigates unrealistic images and label ambiguity, improving the performance and adversarial robustness of the resulting models.
  arXiv  Detail & Related papers  (2024-12-03T10:45:34Z)
• Deep Learning Based Speckle Filtering for Polarimetric SAR Images. Application to Sentinel-1 [51.404644401997736]
  We propose a complete framework to remove speckle in polarimetric SAR images using a convolutional neural network. Experiments show that the proposed approach offers exceptional results in both speckle reduction and resolution preservation.
  arXiv  Detail & Related papers  (2024-08-28T10:07:17Z)
• Few-Shot Image Generation by Conditional Relaxing Diffusion Inversion [37.18537753482751]
  Conditional Diffusion Relaxing Inversion (CRDI) is designed to enhance distribution diversity in synthetic image generation. CRDI does not rely on fine-tuning based on only a few samples. It focuses on reconstructing each target image instance and expanding diversity through few-shot learning.
  arXiv  Detail & Related papers  (2024-07-09T21:58:26Z)
• DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [55.48770333927732]
  We propose a Difusion-based Anomaly Detection (DiAD) framework for multi-class anomaly detection. It consists of a pixel-space autoencoder, a latent-space Semantic-Guided (SG) network with a connection to the stable diffusion's denoising network, and a feature-space pre-trained feature extractor. Experiments on MVTec-AD and VisA datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-12-11T18:38:28Z)
• PC-GANs: Progressive Compensation Generative Adversarial Networks for Pan-sharpening [50.943080184828524]
  We propose a novel two-step model for pan-sharpening that sharpens the MS image through the progressive compensation of the spatial and spectral information. The whole model is composed of triple GANs, and based on the specific architecture, a joint compensation loss function is designed to enable the triple GANs to be trained simultaneously.
  arXiv  Detail & Related papers  (2022-07-29T03:09:21Z)
• Detecting Deepfakes with Self-Blended Images [37.374772758057844]
  We present novel synthetic training data called self-blended images ( SBIs) to detect deepfakes. SBIs are generated by blending pseudo source and target images from single pristine images. We compare our approach with state-of-the-art methods on FF++, CDF, DFD, DFDC, DFDCP, and FFIW datasets.
  arXiv  Detail & Related papers  (2022-04-18T15:44:35Z)
• A Method for Evaluating Deep Generative Models of Images via Assessing the Reproduction of High-order Spatial Context [9.00018232117916]
  Generative adversarial networks (GANs) are one kind of DGM which are widely employed. In this work, we demonstrate several objective tests of images output by two popular GAN architectures. We designed several context models (SCMs) of distinct image features that can be recovered after generation by a trained GAN.
  arXiv  Detail & Related papers  (2021-11-24T15:58:10Z)
• Image Fine-grained Inpainting [89.17316318927621]
  We present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields. To better train this efficient generator, except for frequently-used VGG feature matching loss, we design a novel self-guided regression loss. We also employ a discriminator with local and global branches to ensure local-global contents consistency.
  arXiv  Detail & Related papers  (2020-02-07T03:45:25Z)

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.