发表机构
Northeastern University（东北大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过干扰状态内容和重路由监督路径，证明扩散分割中的状态依赖由监督路径决定，且扩散计算通常不提供优于仅图像预测的确定性优势。
AI 中文摘要
扩散模型正越来越多地从生成任务适配到条件预测任务，其中条件信号与目标的演化噪声表示相结合。然而，在完全监督的分割任务中，条件图像本身已足以支持直接的目标预测，因此仅凭端点性能既不能证明模型依赖于所添加的扩散状态，也不能证明其相对于仅使用图像的预测具有确定性优势。为了考察状态依赖性，我们在三个数据集上对十二种已发表的方法进行重训练时，干扰了源自目标的状态内容或破坏了图像-状态配对，每种设置使用十个匹配的随机种子。所有40个原始方法比较中，其评估掩码路径位于噪声量重建下游的，均表现出状态依赖性；而所有30个具有分割监督旁路的比较则保持了参考性能。通过强制分割监督经过噪声到掩码重建，将五种原本具有旁路能力的方法重新路由，使得所有30个相应的比较从保持性能转变为状态依赖。对于确定性效用，匹配的仅图像对应方法在总共35个设置中的28个中取得了相似或更好的性能，其中包括20个原生方法依赖所审计的两个状态属性中的16个。这些结果表明，监督路径是所审计方法中状态依赖性的决定因素。此外，匹配的仅图像对应方法表明，扩散特有的计算通常不提供确定性端点优势，包括在依赖所审计状态属性的方法中也是如此。更一般地，当条件信号已经支持强目标预测时，扩散特有的主张需要额外的证据，证明所添加的状态被使用，并且扩散特有的计算相对于匹配的仅条件对应方法改善了所声称的能力。
英文摘要
Diffusion models are increasingly adapted from generation to conditional prediction, where a conditioning signal is combined with an evolving noisy representation of the target. In fully supervised segmentation, however, the conditioning image can already support direct target prediction, so endpoint performance alone establishes neither reliance on the added diffusion state nor a deterministic advantage over image-only prediction. For state reliance, we disrupt target-derived state content or correct image-state pairing during retraining of twelve published methods across three datasets, with ten matched seeds per setting. All 40 original-method comparisons whose evaluated-mask routes remained downstream of noised-quantity reconstruction exhibited state reliance, whereas all 30 comparisons with a segmentation-supervised bypass preserved reference performance. Rerouting five originally bypass-capable methods by forcing segmentation supervision through noise-to-mask reconstruction converted all 30 corresponding comparisons from preserved performance to state reliance. For deterministic utility, matched image-only counterparts achieved similar or better performance in 28 of 35 settings overall, including 16 of 20 whose native methods relied on both audited state properties. These results identify supervision path as a determinant of state reliance in the audited methods. Separately, matched image-only counterparts show that diffusion-specific computation often provides no deterministic endpoint advantage, including in methods that rely on the audited state properties. More generally, when conditioning already supports strong target prediction, diffusion-specific claims require additional evidence that the added state is used and that diffusion-specific computation improves the claimed capability beyond a matched condition-only counterpart.
