State-Isolated Vision Mamba via Update-Tendency Routing for Underwater Image Enhancement

Key points

• 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?1
• Based on this observation, we introduce State Isolation, a new recurrent state organization principle for Vision Mamba,tokens with compatible state-update tendencies evolve within independent recurrent state streams.1
• To instantiate this principle, we propose 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 cluster--route--isolate paradigm.1
• In addition, we develop a dynamic channel-wise reweighting objective to compensate for wavelength-dependent reconstruction difficulty in underwater images.1

Sources (1)

• [1]State-Isolated Vision Mamba via Update-Tendency Routing for Underwater Image Enhancement
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 03:18 PM

  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?

Extractive summary: sentences quoted from the sources.