用于水下图像增强的、基于更新倾向路由的状态隔离视觉Mamba
State-Isolated Vision Mamba via Update-Tendency Routing for Underwater Image Enhancement
AI总结：
针对水下图像增强中视觉Mamba的状态争用问题，提出基于更新倾向路由的状态隔离视觉Mamba（IsoMamba），在多基准上实现SOTA性能，验证了状态隔离循环建模的有效性。
摘要：
视觉Mamba近期成为卷积和基于Transformer架构的高效替代方案，它通过循环状态演化对长距离空间依赖进行建模。现有研究主要改进token序列化、扫描策略或专家路由，但很大程度上忽略了一个状态层面的问题：如何为空间异质性视觉恢复组织循环状态？本文表明，迫使具有异质性更新行为的token循环修改共享隐藏状态会导致持续的跨内容干扰，我们将其称为“状态争用”。我们进一步指出，有效的循环建模应根据token兼容性而非token排序来组织状态演化。基于这一观察，我们提出“状态隔离”，这是一种用于视觉Mamba的新型循环状态组织原则：具有兼容状态更新倾向的token在独立的循环状态流中演化。为实例化该原则，我们提出IsoMamba，一种Δ引导的架构，它构建模型内在更新表示，通过无标签聚类发现更新兼容的token组，并按照“聚类-路由-隔离”范式将它们路由到隔离的Mamba专家。此外，我们开发了一种动态通道级重加权目标，以补偿水下图像中与波长相关的重建难度。大量实验表明，IsoMamba在多个水下图像增强基准上始终达到最先进的性能，同时提供更清晰的隐藏状态响应，验证了状态隔离循环建模的有效性。
英文摘要：
Vision Mamba has recently emerged as an efficient alternative to convolutional and Transformer-based architectures by modeling long-range spatial dependencies through recurrent state evolution. Existing studies primarily improve token serialization, scanning strategies, or expert routing, yet largely overlook a state level question question: how should recurrent states be organized for spatially heterogeneous visual restoration? In this paper, we show that forcing tokens with heterogeneous update behaviors to recurrently modify a shared hidden state leads to persistent cross-content interference, which we term \textbf{State Contention}. We further argue that effective recurrent modeling should organize state evolution according to token compatibility rather than token ordering. Based on this observation, we introduce \textbf{State Isolation}, a new recurrent state organization principle for Vision Mamba,tokens with compatible state-update tendencies evolve within independent recurrent state streams. To instantiate this principle, we propose \textbf{IsoMamba}, a $Δ$-guided architecture that constructs model-intrinsic update representations, discovers update-compatible token groups through label-free clustering, and routes them to isolated Mamba experts following a \textbf{cluster--route--isolate} paradigm. In addition, we develop a dynamic channel-wise reweighting objective to compensate for wavelength-dependent reconstruction difficulty in underwater images. Extensive experiments demonstrate that IsoMamba consistently achieves state-of-the-art performance on multiple underwater image enhancement benchmarks while providing cleaner hidden state responses, validating the effectiveness of state isolated recurrent modeling.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
