TopoLoRA-SAM: Topology-Aware Parameter-Efficient Adaptation of Foundation Segmenters for Thin-Structure and Cross-Domain Binary Semantic Segmentation

2026-01-05 · Salim Khazem arxiv

Foundation segmentation models such as the Segment Anything Model (SAM) exhibit strong zero-shot generalization through large-scale pretraining, but adapting them to domain-specific semantic segmentation remains challenging, particularly for thin structures (e.g., retinal vessels) and noisy modalities (e.g., SAR imagery). Full fine-tuning is computationally expensive and risks catastrophic forgetting. We propose \textbf{TopoLoRA-SAM}, a topology-aware and parameter-efficient adaptation framework for binary semantic segmentation. TopoLoRA-SAM injects Low-Rank Adaptation (LoRA) into the frozen ViT encoder, augmented with a lightweight spatial convolutional adapter and optional topology-aware supervision via differentiable clDice. We evaluate our approach on five benchmarks spanning retinal vessel segmentation (DRIVE, STARE, CHASE\_DB1), polyp segmentation (Kvasir-SEG), and SAR sea/land segmentation (SL-SSDD), comparing against U-Net, DeepLabV3+, SegFormer, and Mask2Former. TopoLoRA-SAM achieves the best retina-average Dice and the best overall average Dice across datasets, while training only \textbf{5.2\%} of model parameters ($\sim$4.9M). On the challenging CHASE\_DB1 dataset, our method substantially improves segmentation accuracy and robustness, demonstrating that topology-aware parameter-efficient adaptation can match or exceed fully fine-tuned specialist models. Code is available at : https://github.com/salimkhazem/Seglab.git

📄 PDF Abstract BibTeX arXiv:2601.02273

Code (0)

등록된 구현이 없습니다.

Tasks

Retinal Vessel Segmentation Zero-shot Generalization Semantic Segmentation Polyp Segmentation

LoCA: Spatially-Aware Low-Rank Convolutional Adaptation of Vision Foundation Models

2026-07-08 · Sojung An, Junha Lee, Sujeong You, Nam Ik Cho 외 arxiv

Pre-trained Vision Foundation Models (VFMs) provide strong visual representations for diverse downstream tasks. The key challenge of VFM adaptation stems from the prohibitive costs of full fine-tuning and catastrophic fo…

parameter-efficient fine-tuning Semantic Segmentation

Stabilizing Decentralized Federated Fine-Tuning via Topology-Aware Alternating LoRA

2026-01-31 · Xiaoyu Wang, Xiaotian Li, Zhixiang Zhou, Chen Li 외 arxiv

Decentralized federated learning (DFL), a serverless variant of federated learning, poses unique challenges for parameter-efficient fine-tuning due to the factorized structure of low-rank adaptation (LoRA). Unlike linear…

parameter-efficient fine-tuning Federated Learning

Multi-Task Crack Foundation Model for Engineering-Reliable Crack Representation and Topology Preservation in Civil Infrastructure

2026-06-04 · Blessing Agyei Kyem, Joshua Kofi Asamoah, Eugene Denteh, Armstrong Aboah arxiv

Reliable crack assessment requires not only accurate pixel-level masks but also connected crack geometry and confidence estimates that remain stable under domain shift. However, existing segmentation models can achieve h…

LUMINA: A Grid Foundation Model for Benchmarking AC Optimal Power Flow Surrogate Learning

2026-05-04 · Hongwei Jin, Keunju Song, Zeeshan Memon, Yijiang Li 외 arxiv

AC optimal power flow (ACOPF) is foundational yet computationally expensive in power grid operations, driving learning-based surrogates for large-scale grid analysis. These surrogates, however, often fail to generalize a…

FedTaste: Topology-Aware Structural Transfer for Multimodal Federated Learning with Missing Modalities

2026-07-25 · Haochen Liang, Jie Zhang, Hideya Ochiai arxiv

Multimodal Federated Learning is often challenged by arbitrary modality missingness and Non-IID data distributions, which lead to severe representation drift and hinder effective collaboration across clients. Existing me…

Federated Learning