# Boundary-Aligned Contribution Routing for Robust Optical--SAR Object Detection

arXiv: https://arxiv.org/abs/2608.15261 · HTML: https://mlsanity.com/paper/2608.15261/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 68 references that are in the map.
- First posted on arXiv 15 Aug 2026.

## Builds on (most cited first, 30 of 34)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Multimodal Learning with Transformers: A Survey](https://mlsanity.com/paper/2206.06488/) (2022)
- [Multimodal Deep Learning](https://mlsanity.com/paper/2301.04856/) (2023)
- [Are Multimodal Transformers Robust to Missing Modality?](https://mlsanity.com/paper/2204.05454/) (2022)
- [Cross Modal Distillation for Supervision Transfer](https://mlsanity.com/paper/1507.00448/) (2015)
- [Trusted Multi-View Classification with Dynamic Evidential Fusion](https://mlsanity.com/paper/2204.11423/) (2022)
- [Channel-wise Knowledge Distillation for Dense Prediction](https://mlsanity.com/paper/2011.13256/) (2020)
- [Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling](https://mlsanity.com/paper/2307.14126/) (2023)
- [Semantic Image Inpainting with Deep Generative Models](https://mlsanity.com/paper/1607.07539/) (2016)
- [mmFormer: Multimodal Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation](https://mlsanity.com/paper/2206.02425/) (2022)
- [ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection](https://mlsanity.com/paper/2308.07504/) (2023)
- [Deep Learning in Multimodal Remote Sensing Data Fusion: A Comprehensive Review](https://mlsanity.com/paper/2205.01380/) (2022)
- [Cross Modal Transformer: Towards Fast and Robust 3D Object Detection](https://mlsanity.com/paper/2301.01283/) (2023)
- [Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts](https://mlsanity.com/paper/2410.08245/) (2024)
- [Multimodal Deep Learning for Robust RGB-D Object Recognition](https://mlsanity.com/paper/1507.06821/) (2015)
- [M3AE: Multimodal Representation Learning for Brain Tumor Segmentation with Missing Modalities](https://mlsanity.com/paper/2303.05302/) (2023)
- [SpaceNet 6: Multi-Sensor All Weather Mapping Dataset](https://mlsanity.com/paper/2004.06500/) (2020)
- [SuperYOLO: Super Resolution Assisted Object Detection in Multimodal Remote Sensing Imagery](https://mlsanity.com/paper/2209.13351/) (2022)
- [Cross-Modality Attentive Feature Fusion for Object Detection in Multispectral Remote Sensing Imagery](https://mlsanity.com/paper/2112.02991/) (2021)
- [Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions](https://mlsanity.com/paper/2107.13782/) (2021)
- [SimMLM: A Simple Framework for Multi-modal Learning with Missing Modality](https://mlsanity.com/paper/2507.19264/) (2025)
- [Calibrating Multimodal Learning](https://mlsanity.com/paper/2306.01265/) (2023)
- [Resilient Sensor Fusion under Adverse Sensor Failures via Multi-Modal Expert Fusion](https://mlsanity.com/paper/2503.19776/) (2025)
- [Feature-enhanced Generation and Multi-modality Fusion based Deep Neural Network for Brain Tumor Segmentation with Missing MR Modalities](https://mlsanity.com/paper/2111.04735/) (2021)
- [MaDiNet: Mamba Diffusion Network for SAR Target Detection](https://mlsanity.com/paper/2411.07500/) (2024)

## Abstract (arXiv)

Optical imagery provides rich appearance cues, whereas synthetic aperture radar (SAR) offers observations that are less sensitive to illumination and weather, making optical--SAR fusion attractive for remote-sensing object detection. However, the presence of multiple modalities does not guarantee beneficial fusion: imperfect spatial, temporal, and semantic correspondence can make an otherwise intact stream conditionally harmful and induce negative cross-modal transfer. We handle this issue through a model-specific task-utility perspective and learn task-conditioned contribution routing using detection supervision alone. The proposed fusion-boundary-aligned routing regulates each modality's contribution before the first learned cross-modal feature-value mixing operation. For architectures with frequent shallow interaction, a Feature Router performs cross-conditioned, group-addressable modulation near the input; for dual-backbone architectures, a Dual-Statistic Semantic Router predicts stream-level contribution weights from modality-specific average and maximum statistics before late semantic fusion. The routers require no explicit utility supervision, quality labels, reconstruction, or distillation. Experiments on M4-SAR and SpaceNet6-OTD cover nominal full inputs, controlled correspondence shifts, missing modalities, and four nonzero modality-corruption scenarios. Across the reported clean-training controls, routing improves full-input mAP50 by 0.5--5.9 points. Relative to the corresponding modality-dropout baselines, it raises missing-modality mAP50 by 7.6--41.6 points and reduces the negative-transfer rate by up to 12.7 percentage points. Spearman correlations between the learned routing weights and model-specific leave-one-modality-out utility range from 0.45 to 0.66, supporting the task-utility interpretation of the routing coefficients.