Keywords
edge filtering
attention mechanism
semantic segmentation
multimodal learning
Abstract
Complex visual tasks such as semantic segmentation, salient object detection, and multimodal object detection often suffer from ambiguous boundaries, modality redundancy, and inconsistent feature alignment across different input modalities. Existing fusion strategies typically treat cross-modal features as a homogeneous tensor and apply uniform attention weighting, which fails to preserve fine-grained edge information while suppressing irrelevant noise. This paper proposes a Cross-Modal Edge Filtering and Attention Fusion (CEFAF) network that explicitly decouples edge-preserving and semantic-level fusion through a dual-branch design. The method introduces an Edge-Guided Frequency Filtering (EGFF) module that decomposes each modality into high-frequency edge components and low-frequency semantic components using learnable wavelet decomposition, followed by a Cross-Modal Attention Fusion (CMAF) module that adaptively recalibrates channel and spatial weights across modalities. Extensive experiments on three public benchmarks—MFNet for RGB-T semantic segmentation, NJU2K for RGB-D salient object detection, and LLVIP for infrared-visible pedestrian detection—demonstrate that CEFAF achieves state-of-the-art performance. On MFNet, CEFAF improves mean Intersection over Union (mIoU) by 3.2% over the strongest baseline, while reducing boundary error by 18.7%. Ablation studies validate the contribution of each component, and visualization results confirm that edge-preserving fusion substantially improves boundary localization in challenging scenes with occlusions and low illumination.
References
Mini Han Wang , " AI-Powered Innovations in Ophthalmic Diagnosis and Treatment ", Bentham Science Publishers (2025). https://doi.org/10.2174/97988988122871250101
Ye, Z., Xiao, X., & Wang, H. (2024, July). Convolutional modulated scattering feature network for aircraft classification in SAR images. In IGARSS 2024-2024 IEEE International Geoscience and Remote Sensing Symposium (pp. 9329-9332). IEEE.
Lan, J., Ye, Z., Li, R., Qiu, K., Li, P., Guo, X., & Hu, F. (2026). A Multi-Level Cross-Modal Edge Filtering Method for High-Resolution Optical-SAR Image Registration. Remote Sensing, 18(11), 1741.
Li, P., Ye, Z., & Wang, H. (2026, May). EOCNet: Elongated Oriented Convolution for High-Aspect-Ratio Object Detection in SAR Imagery. In 2026 China Aerospace Information Technology Conference (CAIT) (pp. 1-4). IEEE.
Tan, Y., Cheng, X., Qin, Y., Li, Z., & Zhang, J. (2026). Towards Stable Self-Supervised Object Representations in Unconstrained Egocentric Video. arXiv preprint arXiv:2603.13912.
Wu, H., Song, Y., Zhang, Z., Zhang, Z., Zhou, H., Ma, W. Y., & Liu, J. (2026). Rationalized All-Atom Protein Design with Unified Multi-Modal Bayesian Flow. Advances in Neural Information Processing Systems, 38, 3019-3050.
Jiang, C. (2026). Information doesn’t work? Testing experiential drivers of VR application in heritage tourism by affective-cognitive pathways. Journal of Hospitality and Tourism Technology, 1-28.
Wang, T., & Xia, Z. (2025). Stability of In-Context Learning: A Spectral Coverage Perspective. arXiv preprint arXiv:2509.20677.
Hao, L., Zhang, S., & Schulzrinne, H. (2025, October). Advancing IoT System Dependability: A Deep Dive into Management and Operation Plane Separation. In 2025 IEEE 11th World Forum on Internet of Things (WF-IoT) (pp. 1-6). IEEE.
Huang, Q., Xu, Z., Zhang, X., & Zhang, J. (2025). UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localization. arXiv preprint arXiv:2510.03161.
Ning, E., Gao, W., Liu, Y., Yuan, J., Zhang, H., He, S., & Ning, X. (2026). Causally invariant video anomaly detection via counterfactual reasoning and prototype intervention. Pattern Recognition, 113809.
Yu, Y., Kang, L., & Gao, W. (2026). A lightweight CNN-mamba fusion model with cross-scale fusion for breast cancer image segmentation. Ain Shams Engineering Journal, 17(12), 104470.
Lv, Z., Wang, Q., Gao, W., & Zhou, L. (2026). Enhancing Corporate Green Innovation Under the Green Factory Policy: A Graph Neural Network Approach for Management Decision-Making. Journal of Organizational and End User Computing (JOEUC), 38(1), 1-33.
Lu, B., Li, D., Zhao, K., Ning, E., Gao, W., Dong, J., & Ning, X. (2026). Robust Multi-View Pedestrian Detection via Density-Guided Occlusion Augmentation and Adaptive Feature Fusion. Information Fusion, 104638.
Zhao, R., Zhou, L., Shang, Z., Liu, Y., Zhang, Y., Li, S., ... & Ning, X. (2026). ProMML for robust few-shot adaptation of vision-language models. Pattern Recognition, 114160.
Jia, J., & Zhou, L. (2025). A threat detection scheme for financial big data in internet of things. Frontiers in Physics, 13, 1633021.
Yan, Z., & Lyu, T. (2026). Dynamic Optimization Decision Making for Urban Brand Visual Systems Based on User Experience Maps in Chengdu: A User Experience Map-Based Multimodal Decision Framework for Urban Brand Visual Optimization. Journal of Organizational and End User Computing (JOEUC), 38(1), 1-57.
Huang, T., Huang, C., Li, S., & Lyu, T. (2026). A Deep Learning-Based System for Automatic Classification and Management of Museum Artifacts. Journal of Organizational and End User Computing (JOEUC), 38(1), 1-26.
Dong, J., Shen, Z., Luo, H., Lyu, T., & Gao, W. (2026). Graph attention and text semantics improve personalized recommendation. Scientific Reports.
Wang, X., Liu, S., Qi, Z., Zhou, L., & Cui, Q. (2025). Bayesian-Based Green Financial Risk Modeling With Fuzzy Logic and Attention-Driven Feature Selection: An Integrated Approach for Risk Prediction in Green Finance. Journal of Organizational and End User Computing (JOEUC), 37(1), 1-23.
Zhang, D., Sang, C., & Lyu, T. (2026). Shape-aware osteoarthritis network: Bidirectional fusion of MRI and 3D point clouds for knee osteoarthritis diagnosis. Information Fusion, 104198.
Lv, Z., Wang, Q., Lyu, T., & Dong, J. (2026). A Deep Learning-Based Model for User Emotion Recognition and Behavior Guidance Design: EMoGuideNet-An Emotion-Aware Multimodal Framework for Enhancing Intelligent User Interaction. Journal of Organizational and End User Computing (JOEUC), 38(1), 1-30.
Lyu, M., Guo, J., Gao, W., & Lyu, T. (2026). Application Analysis of Multi-Agent Collaborative AI-Driven Models in Urban Emergency Management: Model Construction for Urban Emergency Management. Journal of Organizational and End User Computing (JOEUC), 38(1), 1-26.
Huang, C., Jia, Z., Fei, H., Zhu, Y., Yuan, Z., Zhang, J., & Zhou, J. (2025, April). Semantic to structure: Learning structural representations for infringement detection. In ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1-5). IEEE.
Chen, B., Zuo, H., Liao, Y., & Li, Z. (2024, December). A Data-Driven Analysis of Mental Health Status and Early Warning System for Vocational College Students. In 2024 5th International Conference on Information Science and Education (ICISE-IE) (pp. 312-315). IEEE.
Xu, Z., Zhang, X., Li, R., Tang, Z., Huang, Q., & Zhang, J. (2024). Fakeshield: Explainable image forgery detection and localization via multi-modal large language models. arXiv preprint arXiv:2410.02761.
Jia, Z., & Huang, C. (2025). Automated Framework for Extracting and Restoring Minutiae From Low-Quality Fingerprints. IEEE Signal Processing Letters.
Wu, J., & Zuo, H. (2024, November). Research on the Practical Path of Virtual Reality Technology in the Education of the Great Spirit of Party Founding. In 2024 5th International Conference on Modern Education and Information Management (ICMEIM 2024) (pp. 288-295). Atlantis Press.
Zhang, Y., Yang, Z., Chen, J., Qi, Z., & Yang, G. (2019, August). Presentation, derivation and numerical experiments of a group of extrapolation formulas. In 2019 9th International Conference on Information Science and Technology (ICIST) (pp. 240-246). IEEE.
Que, H. H., Jin, Y., Wang, T., Liu, M. K., Yang, X. H., & Qiao, F. (2023). A Survey of Approximate Computing: From Arithmetic Units Design to High-Level Applications. Journal of Computer Science and Technology, 38(2), 251-272.
Zhu, H., Huang, X., Gao, H., Jiang, M., Que, H., & Mu, L. (2025, July). A Wireless Collaborated Inference Acceleration Framework for Plant Disease Recognition. In International Conference on Intelligent Computing (pp. 331-341). Singapore: Springer Nature Singapore.
Xi, X., Chen, P., Qiu, Y., Luo, R., Tong, P., & Liang, J. Video-BCI: Bayesian Cognitive Integration of Self-Prior Hypotheses for Video Understanding. In Forty-third International Conference on Machine Learning.
Liang, J., Xiao, Y., Yang, H., Yu, Z., Liu, J. N., & Yang, K. (2026, April). C-HyPOD: Causal Hyperbolic Representation Learning with Prototype Orthogonal Disentanglement for Graph Out-of-Distribution Recommendation. In Proceedings of the ACM Web Conference 2026 (pp. 6541-6550).
Chen, Q. (2026, March). RADR-MO: Resilience-Aware Dynamic Re-routing via Graph Attention Networks and Multi-Objective Meta-Reinforcement Learning for Supply Chain Resilience. In Proceedings of the 2026 3rd International Conference on Innovation Management and Information Systems (pp. 155-162).
Cheng, X., Qin, Y., Tan, Y., Li, Z., Wang, Y., Xiao, H., & Zhang, Y. (2026). Psymem: Fine-grained psychological alignment and explicit memory control for advanced role-playing llms. Transactions of the Association for Computational Linguistics, 14, 510-529.
Yang, J., Li, Q., Yu, H., Wang, X., Wang, C., Ma, B., ... & Li, X. (2026). Invisible Image Watermark Attacks: A Survey.
Zhou, Y., Yao, J., Liu, Y., Dong, Z., Ye, W., Wen, J., & Choi, L. Y. (2026). Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity. arXiv preprint arXiv:2608.02665.
Su, J., Zhu, F., Shi, H., Han, T., Qiu, Y., Luo, J., ... & Gao, J. (2025). MAN++: Scaling Momentum Auxiliary Network for Supervised Local Learning in Vision Tasks. arXiv preprint arXiv:2507.16279.
C. Wan, Y. Luo, W. Wu, N. D. Hatziargyriou and S. Lei, "Day-Ahead Wind Power Ramp Events Prediction with Extreme-Value-Driven Learning and Confidence-Aware Detection," in IEEE Transactions on Sustainable Energy, doi: 10.1109/TSTE.2026.3669605.
Quan, Q., Gao, Y., & Wang, Q. (2025). The impact of teacher emotional support on students' engagement in AI-mediated English learning environments: The mediating role of resilience and self-efficacy. Acta Psychologica, 260, 105766.
Xu, Y., Sun, Y., Zhai, B., Li, M., Liang, W., Li, Y., & Du, S. (2025, April). Zero-shot video moment retrieval via off-the-shelf multimodal large language models. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 9, pp. 8978-8986).
Zheng, X., Chen, X., Gong, S., Griffin, X., & Slabaugh, G. (2025, September). Xfmamba: Cross-fusion mamba for multi-view medical image classification. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 672-682). Cham: Springer Nature Switzerland.
Yu, C., Wang, H., Chen, J., Wang, Z., Deng, B., Hao, Z., ... & Song, Y. (2026). When Rules Fall Short: Agent-Driven Discovery of Emerging Content Issues in Short Video Platforms. arXiv preprint arXiv:2601.11634.
Wu, X., Gao, D., Yao, J., Qian, Q., & Song, J. (2025). Optimization of Single-Track Train Schedules with Cyclic Operation Strategies. In H. Fujita, A. Hernandez-Matamoros, & Y. Watanobe (Eds.), Proceedings of the 24th International Conference on New Trends in Intelligent Software Methodologies, Tools and Techniques (SoMeT_25) (pp. 197-206). (Frontiers in Artificial Intelligence and Applications; Vol. 411). IOS Press BV. https://doi.org/10.3233/FAIA250522
Liu, T., He, J., Zhou, R., Song, J., Liu, H., & Liang, Y. (2025). Revolutionizing clinical decision making through deep learning and topic modeling for pathway optimization. Scientific Reports, 15(1), Article 28787. https://doi.org/10.1038/s41598-025-12679-z
Ma, C., Song, J., Xu, Y., Fan, H., Wu, X., & Sun, T. (2024). Vehicle-Based Machine Vision Approaches in Intelligent Connected System. IEEE Transactions on Intelligent Transportation Systems, 25(3), 2827-2836. https://doi.org/10.1109/TITS.2023.3276325
Zuo, H., Lim, K. H., Sivaraman, E., & Phang, J. T. S. (2024, November). Eye Movement Analysis using Virtual Reality in Early Detection of Alzheimer’s Disease. In 2024 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) (pp. 1690-1694). IEEE.
Li, L., Wang, T., Li, X., Huang, P., Guo, Y., Lu, L., ... & Zeng, G. (2023). Continuous-variable quantum key distribution with on-chip light sources. Photonics Research, 11(4), 504-516.
Wang, T., Huang, P., Li, L., Zhou, Y., & Zeng, G. (2024). High key rate continuous-variable quantum key distribution using telecom optical components. New Journal of Physics, 26(2), 023002.
Dong, J., Wang, T., Li, L., Huang, P., & Zeng, G. (2022). Efficient frame synchronization using a weak coherent state for continuous-variable quantum key distribution. Physical Review A, 105(5), 052407.