# SAM2LoRA: Composite Loss-Guided, Parameter-Efficient Finetuning of SAM2 for Retinal Fundus Segmentation

arXiv: https://arxiv.org/abs/2510.10288 · HTML: https://mlsanity.com/paper/2510.10288/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 37 references that are in the map.
- First posted on arXiv 11 Oct 2025.

## Builds on (most cited first, 14 of 14)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)
- [A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation](https://mlsanity.com/paper/1810.07842/) (2018)
- [Medical SAM 2: Segment medical images as video via Segment Anything Model 2](https://mlsanity.com/paper/2408.00874/) (2024)
- [REFUGE2 Challenge: A Treasure Trove for Multi-Dimension Analysis and Evaluation in Glaucoma Screening](https://mlsanity.com/paper/2202.08994/) (2022)
- [An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models](https://mlsanity.com/paper/2309.09958/) (2023)
- [G1020: A Benchmark Retinal Fundus Image Dataset for Computer-Aided Glaucoma Detection](https://mlsanity.com/paper/2006.09158/) (2020)
- [Unleashing the Potential of SAM2 for Biomedical Images and Videos: A Survey](https://mlsanity.com/paper/2408.12889/) (2024)
- [Full-scale Representation Guided Network for Retinal Vessel Segmentation](https://mlsanity.com/paper/2501.18921/) (2025)
- [Assessing glaucoma in retinal fundus photographs using Deep Feature Consistent Variational Autoencoders](https://mlsanity.com/paper/2110.01534/) (2021)

## Built on by (most cited first, 3 of 3)

- [SAMSEM -- A Generic and Scalable Approach for IC Metal Line Segmentation](https://mlsanity.com/paper/2603.16548/) (2026)
- [Lean-SAM2: Target-Anchored Memory and Encoder Acceleration for SAM2](https://mlsanity.com/paper/2607.19811/) (2026)
- [Topology-Aware Parameter-Efficient Adaptation for Cross-Dataset Retinal Vessel Segmentation](https://mlsanity.com/paper/2609.26189/) (2026)

## Abstract (arXiv)

We propose SAM2LoRA, a parameter-efficient fine-tuning strategy that adapts the Segment Anything Model 2 (SAM2) for fundus image segmentation. SAM2 employs a masked autoencoder-pretrained Hierarchical Vision Transformer for multi-scale feature decoding, enabling rapid inference in low-resource settings; however, fine-tuning remains challenging. To address this, SAM2LoRA integrates a low-rank adapter into both the image encoder and mask decoder, requiring fewer than 5% of the original trainable parameters. Our analysis indicates that for cross-dataset fundus segmentation tasks, a composite loss function combining segmentationBCE, SoftDice, and FocalTversky losses is essential for optimal network tuning. Evaluated on 11 challenging fundus segmentation datasets, SAM2LoRA demonstrates high performance in both blood vessel and optic disc segmentation under cross-dataset training conditions. It achieves Dice scores of up to 0.86 and 0.93 for blood vessel and optic disc segmentation, respectively, and AUC values of up to 0.98 and 0.99, achieving state-of-the-art performance while substantially reducing training overhead.