{"ID":2822659,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.02273","arxiv_id":"2601.02273","title":"TopoLoRA-SAM: Topology-Aware Parameter-Efficient Adaptation of Foundation Segmenters for Thin-Structure and Cross-Domain Binary Semantic Segmentation","abstract":"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","short_abstract":"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 imager...","url_abs":"https://arxiv.org/abs/2601.02273","url_pdf":"https://arxiv.org/pdf/2601.02273v1","authors":"[\"Salim Khazem\"]","published":"2026-01-05T17:03:45Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.LG\"]","methods":"[\"LoRA\"]","has_code":false,"code_links":[{"ID":605432,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2822659,"paper_url":"https://arxiv.org/abs/2601.02273","paper_title":"TopoLoRA-SAM: Topology-Aware Parameter-Efficient Adaptation of Foundation Segmenters for Thin-Structure and Cross-Domain Binary Semantic Segmentation","repo_url":"https://github.com/salimkhazem/Seglab.git","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}