# TauFlow: Dynamic Causal Constraint for Complexity-Adaptive Lightweight Segmentation

arXiv: https://arxiv.org/abs/2511.07057 · HTML: https://mlsanity.com/paper/2511.07057/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- First posted on arXiv 10 Nov 2025.

## Abstract (arXiv)

Deploying lightweight medical image segmentation models on edge devices presents two major challenges: 1) efficiently handling the stark contrast between lesion boundaries and background regions, and 2) the sharp drop in accuracy that occurs when pursuing extremely lightweight designs (e.g., <0.5M parameters). To address these problems, this paper proposes TauFlow, a novel lightweight segmentation model. The core of TauFlow is a dynamic feature response strategy inspired by brain-like mechanisms. This is achieved through two key innovations: the Convolutional Long-Time Constant Cell (ConvLTC), which dynamically regulates the feature update rate to "slowly" process low-frequency backgrounds and "quickly" respond to high-frequency boundaries; and the STDP Self-Organizing Module, which significantly mitigates feature conflicts between the encoder and decoder, reducing the conflict rate from approximately 35%-40% to 8%-10%.