Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection

• URL: http://arxiv.org/abs/2411.15633v2
• Date: Fri, 31 Jan 2025 17:31:54 GMT
• Title: Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection
• Authors: Zhiyuan Yan, Jiangming Wang, Peng Jin, Ke-Yue Zhang, Chengchun Liu, Shen Chen, Taiping Yao, Shouhong Ding, Baoyuan Wu, Li Yuan,
• Abstract summary: A naively trained detector tends to favor overfitting to the limited and monotonous fake patterns, causing the feature space to become highly constrained and low-ranked. One potential remedy is incorporating the pre-trained knowledge within the vision foundation models to expand the feature space. By freezing the principal components and adapting only the remained components, we preserve the pre-trained knowledge while learning forgery-related patterns.
• Score: 58.87142367781417
• License:
• Abstract: AI-generated images (AIGIs), such as natural or face images, have become increasingly realistic and indistinguishable, making their detection a critical and pressing challenge. In this paper, we start from a new perspective to excavate the reason behind the failure generalization in AIGI detection, named the \textit{asymmetry phenomenon}, where a naively trained detector tends to favor overfitting to the limited and monotonous fake patterns, causing the feature space to become highly constrained and low-ranked, which is proved seriously limiting the expressivity and generalization. One potential remedy is incorporating the pre-trained knowledge within the vision foundation models (higher-ranked) to expand the feature space, alleviating the model's overfitting to fake. To this end, we employ Singular Value Decomposition (SVD) to decompose the original feature space into two orthogonal subspaces. By freezing the principal components and adapting only the remained components, we preserve the pre-trained knowledge while learning forgery-related patterns. Compared to existing full-parameters and LoRA-based tuning methods, we explicitly ensure orthogonality enabling the higher rank of the whole feature space, effectively minimizing overfitting and enhancing generalization. Extensive experiments with our deep analysis on both deepfake and synthetic image detection benchmarks demonstrate superior generalization performance in detection.

Related papers

• Understanding and Improving Training-Free AI-Generated Image Detections with Vision Foundation Models [68.90917438865078]
  Deepfake techniques for facial synthesis and editing pose serious risks for generative models. In this paper, we investigate how detection performance varies across model backbones, types, and datasets. We introduce Contrastive Blur, which enhances performance on facial images, and MINDER, which addresses noise type bias, balancing performance across domains.
  arXiv  Detail & Related papers  (2024-11-28T13:04:45Z)
• Efficient One-Step Diffusion Refinement for Snapshot Compressive Imaging [8.819370643243012]
  Coded Aperture Snapshot Spectral Imaging (CASSI) is a crucial technique for capturing three-dimensional multispectral images (MSIs) Current state-of-the-art methods, predominantly end-to-end, face limitations in reconstructing high-frequency details. This paper introduces a novel one-step Diffusion Probabilistic Model within a self-supervised adaptation framework for Snapshot Compressive Imaging.
  arXiv  Detail & Related papers  (2024-09-11T17:02:10Z)
• Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities [88.398085358514]
  Contrastive Deepfake Embeddings (CoDE) is a novel embedding space specifically designed for deepfake detection. CoDE is trained via contrastive learning by additionally enforcing global-local similarities.
  arXiv  Detail & Related papers  (2024-07-29T18:00:10Z)
• UniForensics: Face Forgery Detection via General Facial Representation [60.5421627990707]
  High-level semantic features are less susceptible to perturbations and not limited to forgery-specific artifacts, thus having stronger generalization. We introduce UniForensics, a novel deepfake detection framework that leverages a transformer-based video network, with a meta-functional face classification for enriched facial representation.
  arXiv  Detail & Related papers  (2024-07-26T20:51:54Z)
• Weakly Supervised Face and Whole Body Recognition in Turbulent Environments [2.2263723609685773]
  We propose a new weakly supervised framework that generates domain representations, aligning turbulent and pristine images into a common subspace. We also introduce a new tilt map estimator that predicts geometric distortions observed in turbulent images. Our method does not require synthesizing turbulent-free images or ground-truth paired images, and requires significantly fewer annotated samples.
  arXiv  Detail & Related papers  (2023-08-22T19:58:02Z)
• ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstruction [29.370142078092375]
  Most advanced unsupervised anomaly detection (UAD) methods rely on modeling feature representations of frozen encoder networks pre-trained on large-scale datasets. We propose a novel epistemic UAD method, namely ReContrast, which optimize the entire network to reduce biases towards the pre-trained image domain. We conduct experiments across two popular industrial defect detection benchmarks and three medical image UAD tasks, which shows our superiority over current state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-06-05T05:21:15Z)
• When Neural Networks Fail to Generalize? A Model Sensitivity Perspective [82.36758565781153]
  Domain generalization (DG) aims to train a model to perform well in unseen domains under different distributions. This paper considers a more realistic yet more challenging scenario, namely Single Domain Generalization (Single-DG) We empirically ascertain a property of a model that correlates strongly with its generalization that we coin as "model sensitivity" We propose a novel strategy of Spectral Adversarial Data Augmentation (SADA) to generate augmented images targeted at the highly sensitive frequencies.
  arXiv  Detail & Related papers  (2022-12-01T20:15:15Z)
• SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes [7.553507857251396]
  We propose a novel deepfake detector, called SeeABLE, that formalizes the detection problem as a (one-class) out-of-distribution detection task. SeeABLE pushes perturbed faces towards predefined prototypes using a novel regression-based bounded contrastive loss. We show that our model convincingly outperforms competing state-of-the-art detectors, while exhibiting highly encouraging generalization capabilities.
  arXiv  Detail & Related papers  (2022-11-21T09:38:30Z)
• PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models [77.32079593577821]
  PULSE (Photo Upsampling via Latent Space Exploration) generates high-resolution, realistic images at resolutions previously unseen in the literature. Our method outperforms state-of-the-art methods in perceptual quality at higher resolutions and scale factors than previously possible.
  arXiv  Detail & Related papers  (2020-03-08T16:44:31Z)

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.