# S2A:Semantic-to-Spatial Alignment for Alignment-Free RGB-T Salient Object Detection

arXiv: https://arxiv.org/abs/2609.27413 · HTML: https://mlsanity.com/paper/2609.27413/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 40 references that are in the map.
- First posted on arXiv 23 Sep 2026.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [Enhanced-alignment Measure for Binary Foreground Map Evaluation](https://mlsanity.com/paper/1805.10421/) (2018)
- [SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection](https://mlsanity.com/paper/2204.05585/) (2022)
- [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)
- [HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection](https://mlsanity.com/paper/2301.03036/) (2023)
- [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)
- [Unified-modal Salient Object Detection via Adaptive Prompt Learning](https://mlsanity.com/paper/2311.16835/) (2023)
- [Alignment-Free RGB-T Salient Object Detection: A Large-scale Dataset and Progressive Correlation Network](https://mlsanity.com/paper/2412.14576/) (2024)
- [TP-Seg: Task-Prototype Framework for Unified Medical Lesion Segmentation](https://mlsanity.com/paper/2604.00684/) (2026)
- [DifferSeg: Towards Diverse Multimodal Binary Segmentation via Differential Perception and Frequency Guidance](https://mlsanity.com/paper/2606.08906/) (2026)
- [HVPNet: A Bio-Inspired Network for General Salient and Camouflaged Object Detection](https://mlsanity.com/paper/2606.31496/) (2026)
- [RA-SOD: Reliability-Aware RGB-T Salient Object Detection under Modality Degradation](https://mlsanity.com/paper/2609.12622/) (2026)
- [Efficient Fourier Filtering Network with Contrastive Learning for AAV-based Unaligned Bimodal Salient Object Detection](https://mlsanity.com/paper/2411.03728/) (2024)
- [Breaking Alignment Barriers: TPS-Driven Semantic Correlation Learning for Alignment-Free RGB-T Salient Object Detection](https://mlsanity.com/paper/2512.21856/) (2025)
- [TDFNet: Tri-projection Deformable Fusion Network for Panoramic Salient Object Detection](https://mlsanity.com/paper/2608.25808/) (2026)
- [ViCo-SAM3: Vision-Conditioned Alignment for Open-Vocabulary Camouflaged Object Segmentation](https://mlsanity.com/paper/2609.15418/) (2026)

## Abstract (arXiv)

Alignment-free RGB-T salient object detection (RGB-T SOD) aims to identify salient objects from unregistered RGB and thermal image pairs without costly pre-alignment. However, spatial misalignment breaks pixel-wise correspondence and causes feature contamination during cross-modal fusion. To address this issue, we propose S2A, a semantic-to-spatial alignment framework for alignment-free RGB-T SOD. Specifically, a global-guided hierarchical fusion module (GGHF) first exploits global semantic guidance to suppress background interference and refine hierarchical intra-modal features. Subsequently, the alignment-free cross-modal channel attention module (AFCA) globally exchanges complementary semantic information through channel-wise interaction, effectively overcoming the interference caused by local spatial misalignments. Finally, a spatial deformable cross-attention module (SDCA) predicts adaptive sampling offsets to recover local cross-modal spatial correspondence. Through this semantic-to-spatial paradigm, S2A first enables reliable cross-modal semantic interaction and subsequently performs local spatial calibration, effectively reducing misalignment-induced feature contamination. Without bells and whistles, S2A achieves highly competitive performance on multiple public alignment-free RGB-T benchmarks, demonstrating its effectiveness in alleviating misalignment-induced feature contamination.