TauFlow: Dynamic Causal Constraint for Complexity-Adaptive Lightweight Segmentation
This work addresses the problem of accuracy drop in extremely lightweight segmentation models for medical imaging on edge devices, representing an incremental improvement with specific innovations.
The paper tackles the challenges of deploying lightweight medical image segmentation models on edge devices by proposing TauFlow, which uses a dynamic feature response strategy to handle lesion boundaries and background regions efficiently, reducing feature conflict rates from 35%-40% to 8%-10%.
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%.