SAM-DA: Decoder Adapter for Efficient Medical Domain Adaptation
This addresses the computational inefficiency of fine-tuning large models for medical domain adaptation, offering a more tractable solution for researchers and practitioners in medical imaging.
The paper tackles the challenge of adapting the SAM segmentation model to medical images by proposing a decoder adapter that reduces trainable parameters to less than 1% of SAM's total while achieving comparable performance to full fine-tuning, as validated on four datasets.
This paper addresses the domain adaptation challenge for semantic segmentation in medical imaging. Despite the impressive performance of recent foundational segmentation models like SAM on natural images, they struggle with medical domain images. Beyond this, recent approaches that perform end-to-end fine-tuning of models are simply not computationally tractable. To address this, we propose a novel SAM adapter approach that minimizes the number of trainable parameters while achieving comparable performances to full fine-tuning. The proposed SAM adapter is strategically placed in the mask decoder, offering excellent and broad generalization capabilities and improved segmentation across both fully supervised and test-time domain adaptation tasks. Extensive validation on four datasets showcases the adapter's efficacy, outperforming existing methods while training less than 1% of SAM's total parameters.