TauFlow: Dynamic Causal Constraint for Complexity-Adaptive Lightweight Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Zidong, Hassan, Fadratul Hafinaz
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914146936684544
author Chen, Zidong
Hassan, Fadratul Hafinaz
author_facet Chen, Zidong
Hassan, Fadratul Hafinaz
contents 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%.
format Preprint
id arxiv_https___arxiv_org_abs_2511_07057
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TauFlow: Dynamic Causal Constraint for Complexity-Adaptive Lightweight Segmentation
Chen, Zidong
Hassan, Fadratul Hafinaz
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
68U10, 68T45, 92C55, 68T07
I.4.6; I.2.10; J.3; I.2.6
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%.
title TauFlow: Dynamic Causal Constraint for Complexity-Adaptive Lightweight Segmentation
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
68U10, 68T45, 92C55, 68T07
I.4.6; I.2.10; J.3; I.2.6
url https://arxiv.org/abs/2511.07057