用知识蒸馏让SAM模型变小变快，医疗影像分割更实用
Efficient Knowledge Distillation of SAM for Medical Image Segmentation
- 用双损失函数优化编码器和解码器，保留关键特征
- 在多个医学数据集上达到媲美原版的准确率，参数减少显著
- 适合嵌入式设备等算力受限场景，部署更灵活
Segment Anything Model（SAM）在交互式图像分割中树立了新标准，表现出跨任务的强鲁棒性。然而其巨大的计算需求限制了在实时或资源受限环境中的应用。为此，我们提出一种新型知识蒸馏方法KD SAM，通过结合均方误差（MSE）与感知损失，在编码器和解码器层面实现优化。该双损失框架能有效捕捉结构与语义特征，使学生模型在大幅降低计算复杂度的同时保持高分割精度。在Kvasir-SEG、ISIC 2017、Fetal Head Ultrasound和Breast Ultrasound等多个数据集上的评估表明，KD SAM在参数量显著减少的情况下，仍能达到或优于基线模型的性能。该方法有效平衡了分割精度与计算效率，适用于资源受限环境下的实时医疗图像分割应用。
原文摘要 · Abstract (English)
The Segment Anything Model (SAM) has set a new standard in interactive image segmentation, offering robust performance across various tasks. However, its significant computational requirements limit its deployment in real-time or resource-constrained environments. To address these challenges, we propose a novel knowledge distillation approach, KD SAM, which incorporates both encoder and decoder optimization through a combination of Mean Squared Error (MSE) and Perceptual Loss. This dual-loss framework captures structural and semantic features, enabling the student model to maintain high segmentation accuracy while reducing computational complexity. Based on the model evaluation on datasets, including Kvasir-SEG, ISIC 2017, Fetal Head Ultrasound, and Breast Ultrasound, we demonstrate that KD SAM achieves comparable or superior performance to the baseline models, with significantly fewer parameters. KD SAM effectively balances segmentation accuracy and computational efficiency, making it well-suited for real-time medical image segmentation applications in resource-constrained environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。