mlsanityData to 7 Oct 2026

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

arXiv 2601.02273 ↗First posted 5 Jan 2026cs.CV cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (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 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, CHASEDB1), 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 5.2% of model parameters (~4.9M). On the challenging CHASEDB1 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

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 33 of its 43 references that are in the map. First posted on arXiv 5 Jan 2026.

Builds on

33 of 43 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2023Segment Anythingcited by 8,158
  7. 2017On Calibration of Modern Neural Networkscited by 4,860
  8. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  9. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  10. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  11. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  12. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
21 more
  1. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  2. 2022Visual Prompt Tuningcited by 1,674
  3. 2024DoRA: Weight-Decomposed Low-Rank Adaptationcited by 740
  4. 2022AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognitioncited by 714
  5. 2019Kvasir-SEG: A Segmented Polyp Datasetcited by 588
  6. 2023Segment Anything in High Qualitycited by 373
  7. 2021Domain Adaptation for Medical Image Analysis: A Surveycited by 351
  8. 2023AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuningcited by 337
  9. 2022Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuningcited by 292
  10. 2020clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentationcited by 286
  11. 2023Personalize Segment Anything Model with One Shotcited by 250
  12. 2019Topology-Preserving Deep Image Segmentationcited by 198
  13. 2019Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentationcited by 162
  14. 2023SAM-Med2Dcited by 123
  15. 2023Understanding metric-related pitfalls in image analysis validationcited by 57
  16. 2023How to Efficiently Adapt Large Segmentation Model(SAM) to Medical Imagescited by 53
  17. 2022Topologically faithful image segmentation via induced matching of persistence barcodescited by 48
  18. 2025PolygoNet: Leveraging Simplified Polygonal Representation for Effective Image Classificationcited by 6
  19. 2023Improving Knot Prediction in Wood Logs with Longitudinal Feature Propagationcited by 4
  20. 2025Multi-Scale Visual Prompting for Lightweight Small-Image Classificationcited by 2
  21. 2025BYO-Eval: Build Your Own Dataset for Fine-Grained Visual Assessment of Multimodal Language Modelscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026AdapterTune: Zero-Initialized Low-Rank Adapters for Frozen Vision Transformerscited by 3
  2. 2026SAFE-KD: Risk-Controlled Early-Exit Distillation for Vision Backbonescited by 0
  3. 2026Low-Data Supervised Adaptation Outperforms Prompting for Cloud Segmentation Under Domain Shiftcited by 0
  4. 2026MC-RFM: Geometry-Aware Few-Shot Adaptation via Mixed-Curvature Riemannian Flow Matchingcited by 0
  5. 2026Adapting Without Gradients: Affine Statistics Transport and What Its Certificate Can Tell Youcited by 0
  6. 2026Topology-Aware Parameter-Efficient Adaptation for Cross-Dataset Retinal Vessel Segmentationcited by 0