Search papers, labs, and topics across Lattice.
This paper introduces FAN-LoRA, a novel frequency-adaptive fine-tuning architecture designed to enhance the adaptation of the Segment Anything Model (SAM) for medical imaging by addressing severe domain gaps. By decoupling the optimization space into a low-pass branch for global alignment and a high-pass branch for local textural compensation, FAN-LoRA effectively mitigates performance degradation under distribution shifts. Extensive experiments demonstrate that FAN-LoRA outperforms existing parameter-efficient fine-tuning methods, achieving significant improvements in Dice scores and boundary error reductions while maintaining computational efficiency.
FAN-LoRA outperforms existing methods by explicitly decoupling frequency components, leading to significant enhancements in medical image segmentation accuracy.
The advent of vision foundation models, notably the Segment Anything Model (SAM), has catalyzed significant advancements in natural image segmentation. However, their direct transfer to medical imaging remains severely bottlenecked by profound domain gaps, such as cross-modality and cross-center shifts. Existing Parameter-Efficient Fine-Tuning (PEFT) methods facilitate the adaptation of SAM to medical domains; nevertheless, they frequently suffer from performance degradation under severe distribution shifts. This vulnerability primarily stems from the implicit entanglement of heterogeneous frequency components within a shared low-rank subspace, which directly exacerbates sub-optimal structural alignment and localized boundary blurring. To overcome this representational bottleneck, we propose the Fourier-Adaptive Nonlinear Low-Rank Adaptor (FAN-LoRA), a novel frequency-decoupled fine-tuning architecture. FAN-LoRA explicitly separates the optimization space by employing a B-spline-driven low-pass branch for global structural alignment, synergistically coupled with a discrete Fourier high-pass branch for local textural compensation. Extensive experiments across three challenging cross-modality and cross-center benchmarks demonstrate that FAN-LoRA consistently outperforms state-of-the-art PEFT baselines. Compared to the strongest competitors, our method achieves consistent improvements in average Dice scores and notable reductions in boundary errors, while maintaining a compact module size without compromising computational efficiency.
