# S3AM: A Single-Stream SAM with Reliability-Calibrated Frequency Adapter for Multi-modal Salient Object Detection

arXiv: https://arxiv.org/abs/2608.17475 · HTML: https://mlsanity.com/paper/2608.17475/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 43 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Builds on (most cited first, 17 of 17)

- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks](https://mlsanity.com/paper/1907.06781/) (2019)
- [RGBT Salient Object Detection: A Large-scale Dataset and Benchmark](https://mlsanity.com/paper/2007.03262/) (2020)
- [RGB-T Image Saliency Detection via Collaborative Graph Learning](https://mlsanity.com/paper/1905.06741/) (2019)
- [Deep Contrast Learning for Salient Object Detection](https://mlsanity.com/paper/1603.01976/) (2016)
- [A Unified RGB-T Saliency Detection Benchmark: Dataset, Baselines, Analysis and A Novel Approach](https://mlsanity.com/paper/1701.02829/) (2017)
- [CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection](https://mlsanity.com/paper/2112.02363/) (2021)
- [Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection](https://mlsanity.com/paper/2008.07064/) (2020)
- [Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond](https://mlsanity.com/paper/2503.01210/) (2025)
- [MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking](https://mlsanity.com/paper/2107.10433/) (2021)
- [Alignment-Free RGBT Salient Object Detection: Semantics-guided Asymmetric Correlation Network and A Unified Benchmark](https://mlsanity.com/paper/2406.00917/) (2024)
- [Learning Adaptive Fusion Bank for Multi-modal Salient Object Detection](https://mlsanity.com/paper/2406.01127/) (2024)
- [SSFam: Scribble Supervised Salient Object Detection Family](https://mlsanity.com/paper/2409.04817/) (2024)
- [KAN-SAM: Kolmogorov-Arnold Network Guided Segment Anything Model for RGB-T Salient Object Detection](https://mlsanity.com/paper/2504.05878/) (2025)
- [SAMSOD: Rethinking SAM Optimization for RGB-T Salient Object Detection](https://mlsanity.com/paper/2510.03689/) (2025)
- [HyPSAM: Hybrid Prompt-driven Segment Anything Model for RGB-Thermal Salient Object Detection](https://mlsanity.com/paper/2509.18738/) (2025)

## Abstract (arXiv)

Vision foundation models have recently advanced multi-modal salient object detection (MSOD) through parameter-efficient tuning and prompt learning. However, existing Segment Anything Model (SAM)-adapted MSOD methods often rely on dual-stream encoders or auxiliary prompt generators, leading to redundant computation. Although a single-stream alternative can reduce this cost, early fusion may also propagate noisy or misaligned auxiliary high-frequency cues through the backbone. In this paper, we propose a novel single-stream framework that integrates reliability-calibrated frequency adaptation into the adopted SAM backbone for MSOD. It avoids duplicated foundation backbones while explicitly controlling auxiliary frequency injection. Specifically, we design a mixture of frequency experts module, which uses the stationary wavelet transform to decompose each modality and aggregate cross-modal frequency information. We further introduce a reliability-calibrated frequency adapter with a dual-gate calibration mechanism, which selectively propagates the calibrated residual across transformer stages while jointly controlling its injection strength and cross-modal reliability. A hypernetwork-guided semantic-structural decoder then combines semantic mask features from the adopted backbone with Mamba-based structural detail recovery. Comprehensive experiments on RGB-D, RGB-T, and RGB-NIR salient object detection benchmarks validate that the proposed framework achieves competitive performance with only 12.20M trainable parameters, accounting for 5.4% of the total parameters. The code will be available at https://github.com/xuboyue1999/SSSAM.