多样性优于一致性：重新思考生成图像检测中的表征
Diversity over Uniformity: Rethinking Representation in Generated Image Detection
提出反特征坍缩学习框架，通过过滤任务无关成分并抑制伪造线索在表征空间中的过度重叠，保持多样化的判断视角，从而提升生成图像检测模型对未见生成机制的泛化能力。
原文依据 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
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论随着生成模型的快速发展，生成图像检测已成为视觉取证领域的一项重要任务。尽管现有方法已取得显著进展，但它们在训练后往往仅依赖一小部分高度显著的伪造线索，这限制了其泛化到未见生成机制的能力。我们认为，可靠的生成图像检测不应依赖单一决策路径，而应保留多种判断视角，使模型能够从不同角度理解真实图像与生成图像之间的差异。基于这一思想，我们提出了一种反特征坍缩学习框架，该框架过滤任务无关成分并抑制表征空间中不同伪造线索之间的过度重叠，防止判别性信息坍缩至少数主导特征方向。这一设计在模型内部保持了多样且互补的证据，减少了对少量显著线索的依赖，并增强了在未见生成设定下的鲁棒性。在多个公开基准上的大量实验表明，所提方法在跨模型场景下显著优于最优方法，准确率提升5.02%，并展现出更优的泛化性和检测可靠性。源代码已公开于 https://github.com/Yanmou-Hui/DoU。
英文原文摘要 1431 字符
With the rapid advancement of generative models, generated image detection has become an important task in visual forensics. Although existing methods have achieved remarkable progress, they often rely, after training, on only a small subset of highly salient forgery cues, which limits their ability to generalize to unseen generative mechanisms. We argue that reliably generated image detection should not depend on a single decision path but should preserve multiple judgment perspectives, enabling the model to understand the differences between real and generated images from diverse viewpoints. Based on this idea, 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, preventing discriminative information from collapsing into a few dominant feature directions. 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. Extensive experiments on multiple public benchmarks demonstrate that the proposed method significantly outperforms the state-of-the-art approaches in cross-model scenarios, achieving an accuracy improvement of 5.02% and exhibiting superior generalization and detection reliability. The source code is available at https://github.com/Yanmou-Hui/DoU.