# KAN-SAM: Kolmogorov-Arnold Network Guided Segment Anything Model for RGB-T Salient Object Detection

arXiv: https://arxiv.org/abs/2504.05878 · HTML: https://mlsanity.com/paper/2504.05878/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 39 references that are in the map.
- First posted on arXiv 8 Apr 2025.

## Builds on (most cited first, 20 of 20)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [KAN: Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2404.19756/) (2024)
- [Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.12620/) (2023)
- [Dice Loss for Data-imbalanced NLP Tasks](https://mlsanity.com/paper/1911.02855/) (2019)
- [Visual Prompt Multi-Modal Tracking](https://mlsanity.com/paper/2303.10826/) (2023)
- [Wav-KAN: Wavelet Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2405.12832/) (2024)
- [Chebyshev Polynomial-Based Kolmogorov-Arnold Networks: An Efficient Architecture for Nonlinear Function Approximation](https://mlsanity.com/paper/2405.07200/) (2024)
- [TKAN: Temporal Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2405.07344/) (2024)
- [RGBT Salient Object Detection: A Large-scale Dataset and Benchmark](https://mlsanity.com/paper/2007.03262/) (2020)
- [SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection](https://mlsanity.com/paper/2204.05585/) (2022)
- [RGB-T Image Saliency Detection via Collaborative Graph Learning](https://mlsanity.com/paper/1905.06741/) (2019)
- [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)
- [Does Thermal Really Always Matter for RGB-T Salient Object Detection?](https://mlsanity.com/paper/2210.04266/) (2022)
- [Moving Object Segmentation: All You Need Is SAM (and Flow)](https://mlsanity.com/paper/2404.12389/) (2024)
- [Multi-Scale and Detail-Enhanced Segment Anything Model for Salient Object Detection](https://mlsanity.com/paper/2408.04326/) (2024)
- [UV-SAM: Adapting Segment Anything Model for Urban Village Identification](https://mlsanity.com/paper/2401.08083/) (2024)
- [cmSalGAN: RGB-D Salient Object Detection with Cross-View Generative Adversarial Networks](https://mlsanity.com/paper/1912.10280/) (2019)
- [Mirror Complementary Transformer Network for RGB-thermal Salient Object Detection](https://mlsanity.com/paper/2207.03558/) (2022)

## Built on by (most cited first, 4 of 4)

- [HyPSAM: Hybrid Prompt-driven Segment Anything Model for RGB-Thermal Salient Object Detection](https://mlsanity.com/paper/2509.18738/) (2025)
- [M4-SAM: Multi-Modal Mixture-of-Experts with Memory-Augmented SAM for RGB-D Video Salient Object Detection](https://mlsanity.com/paper/2605.11760/) (2026)
- [RDVSv2: A Large-scale Benchmark for RGB-D Video Salient Object Detection](https://mlsanity.com/paper/2607.25392/) (2026)
- [S3AM: A Single-Stream SAM with Reliability-Calibrated Frequency Adapter for Multi-modal Salient Object Detection](https://mlsanity.com/paper/2608.17475/) (2026)

## Abstract (arXiv)

Existing RGB-thermal salient object detection (RGB-T SOD) methods aim to identify visually significant objects by leveraging both RGB and thermal modalities to enable robust performance in complex scenarios, but they often suffer from limited generalization due to the constrained diversity of available datasets and the inefficiencies in constructing multi-modal representations. In this paper, we propose a novel prompt learning-based RGB-T SOD method, named KAN-SAM, which reveals the potential of visual foundational models for RGB-T SOD tasks. Specifically, we extend Segment Anything Model 2 (SAM2) for RGB-T SOD by introducing thermal features as guiding prompts through efficient and accurate Kolmogorov-Arnold Network (KAN) adapters, which effectively enhance RGB representations and improve robustness. Furthermore, we introduce a mutually exclusive random masking strategy to reduce reliance on RGB data and improve generalization. Experimental results on benchmarks demonstrate superior performance over the state-of-the-art methods.