Learning Continuous Source Responses For Generalizable AI-Generated Image Detection

• URL: http://arxiv.org/abs/2609.14316v1
• Date: Sun, 13 Sep 2026 06:24:59 GMT
• Title: Learning Continuous Source Responses For Generalizable AI-Generated Image Detection
• Abstract summary: We introduce CuRe, a framework for learning Continuous Source Responses.<n>CuRe revisits authenticity detection from the perspective of the training task.<n>It achieves an average balanced accuracy of 89.7%, exceeding the second-best method by 5.2 percentage points.
• Score: 42.338483531657666
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Advances in image generation have made synthetic images increasingly difficult to distinguish from real photographs, raising concerns about the trustworthiness of visual media. Existing AI-generated image detectors often perform well on in-domain data, but their robustness and cross-generator generalization remain limited. These limitations are commonly attributed to overfitting to shortcut cues. Although many methods seek to suppress shortcut learning, most retain binary classification as the training task without reconsidering how the task itself shapes the learned representations. We introduce CuRe, a framework for learning Continuous Source Responses that revisits authenticity detection from the perspective of the training task. CuRe reformulates backbone adaptation as regression of real-generated mixing ratios, providing finer supervision that encourages the model to capture authenticity-related variation beyond binary endpoint separation. We further select a compact source-response subspace to suppress nuisance variation and limit the final classifier's access to potential shortcut cues. Across ten public benchmarks, CuRe achieves an average balanced accuracy of 89.7%, exceeding the second-best method by 5.2 percentage points. Further experiments demonstrate consistent generalization gains across visual backbones and strong robustness to common image degradations. Code is available at https://github.com/manic-cui/CuRe

Related papers

• Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement [58.15004031934379]
  We propose Q-DeepSight, a think-with-image framework that emulates this human-like process.<n>Q-DeepSight achieves state-of-the-art performance across diverse benchmarks, including natural, restored, and AI-generated content.<n>We demonstrate its practical value with Perceptual-in-Generation (PiG), a training-free framework where Q-DeepSight's diagnoses guide iterative image enhancement.
  arXiv  Detail & Related papers  (2026-04-18T06:10:57Z)
• Diversity over Uniformity: Rethinking Representation in Generated Image Detection [22.020742109848317]
  We argue that reliably generated image detection should not depend on a single decision path but should preserve multiple judgment perspectives.<n>We propose an anti-feature-collapse learning framework that filters task-irrelevant components and suppresses excessive overlap among different forgery cues in the representation space.<n>This design maintains diverse and complementary evidence within the model, reduces reliance on a small set of salient cues, and enhances robustness under unseen generative settings.
  arXiv  Detail & Related papers  (2026-02-28T15:42:12Z)
• WISER: Wider Search, Deeper Thinking, and Adaptive Fusion for Training-Free Zero-Shot Composed Image Retrieval [36.577766022251446]
  ZS-CIR aims to retrieve target images given a multimodal query without training on triplets annotated.<n>We propose WISER, a training-free framework that unifies T2I and I2I via a "retrieve-verify-refine" pipeline.
  arXiv  Detail & Related papers  (2026-02-26T14:11:10Z)
• Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards [52.90573877727541]
  reinforcement learning (RL) has been considered for diffusion model fine-tuning.<n>RL's effectiveness is limited by the challenge of sparse reward.<n>$textB2text-DiffuRL$ is compatible with existing optimization algorithms.
  arXiv  Detail & Related papers  (2025-03-14T09:45:19Z)
• Robustly Optimized Deep Feature Decoupling Network for Fatty Liver Diseases Detection [18.24448979368885]
  Current medical image classification efforts mainly aim for higher average performance. Without the support of massive data, deep learning faces challenges in fine-grained classification of fatty liver. We propose an innovative deep learning framework that combines feature decoupling and adaptive adversarial training.
  arXiv  Detail & Related papers  (2024-06-25T07:50:09Z)
• Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection [106.39544368711427]
  We study the problem of generalizable synthetic image detection, aiming to detect forgery images from diverse generative methods. We present a novel forgery-aware adaptive transformer approach, namely FatFormer. Our approach tuned on 4-class ProGAN data attains an average of 98% accuracy to unseen GANs, and surprisingly generalizes to unseen diffusion models with 95% accuracy.
  arXiv  Detail & Related papers  (2023-12-27T17:36:32Z)
• Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning [49.43362803584032]
  We propose weakly-supervised image manipulation detection. Such a setting can leverage more training images and has the potential to adapt quickly to new manipulation techniques. Two consistency properties are learned: multi-source consistency (MSC) and inter-patch consistency (IPC)
  arXiv  Detail & Related papers  (2023-09-03T19:19:56Z)
• Towards Robust GAN-generated Image Detection: a Multi-view Completion Representation [27.483031588071942]
  GAN-generated image detection now becomes the first line of defense against the malicious uses of machine-synthesized image manipulations such as deepfakes. We propose a robust detection framework based on a novel multi-view image completion representation. We evaluate the generalization ability of our framework across six popular GANs at different resolutions and its robustness against a broad range of perturbation attacks.
  arXiv  Detail & Related papers  (2023-06-02T08:38:02Z)
• An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation [80.02124918255059]
  Semi-supervised learning aims to boost the accuracy of a model by exploring unlabeled images. We learn two networks to mutually teach each other. The more reliable predictions on easy images in each network are used to teach the other network to learn about the corresponding hard images.
  arXiv  Detail & Related papers  (2020-11-25T03:29:52Z)
• Delving into Inter-Image Invariance for Unsupervised Visual Representations [108.33534231219464]
  We present a study to better understand the role of inter-image invariance learning. Online labels converge faster than offline labels. Semi-hard negative samples are more reliable and unbiased than hard negative samples.
  arXiv  Detail & Related papers  (2020-08-26T17:44:23Z)

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.