SAMwave: Wavelet-Driven Feature Enrichment for Effective Adaptation of Segment Anything Model

TL;DR

SAMwave introduces a wavelet-based feature enrichment technique that significantly improves the adaptation of the Segment Anything Model for complex low-level vision tasks, outperforming existing methods.

Contribution

It proposes a novel wavelet transform-based approach with complex-valued adapters for better feature extraction and adaptation of SAM in dense prediction tasks.

Findings

Outperforms existing adaptation methods on four low-level vision tasks

Effective across both SAM and SAM2 backbones

Works with real and complex-valued adapters

Abstract

The emergence of large foundation models has propelled significant advances in various domains. The Segment Anything Model (SAM), a leading model for image segmentation, exemplifies these advances, outperforming traditional methods. However, such foundation models often suffer from performance degradation when applied to complex tasks for which they are not trained. Existing methods typically employ adapter-based fine-tuning strategies to adapt SAM for tasks and leverage high-frequency features extracted from the Fourier domain. However, Our analysis reveals that these approaches offer limited benefits due to constraints in their feature extraction techniques. To overcome this, we propose \textbf{\textit{SAMwave}}, a novel and interpretable approach that utilizes the wavelet transform to extract richer, multi-scale high-frequency features from input data. Extending this, we introduce complex-valued adapters capable of capturing complex-valued spatial-frequency information via complex wavelet transforms. By adaptively integrating these wavelet coefficients, SAMwave enables SAM's encoder to capture information more relevant for dense prediction. Empirical evaluations on four challenging low-level vision tasks demonstrate that SAMwave significantly outperforms existing adaptation methods. This superior performance is consistent across both the SAM and SAM2 backbones and holds for both real and complex-valued adapter variants, highlighting the efficiency, flexibility, and interpretability of our proposed method for adapting segment anything models.