TauFlow: Dynamic Causal Constraint for Complexity-Adaptive Lightweight Segmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| 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 |