Multimodal object detection improves robustness in chal- lenging conditions by leveraging complementary cues from multiple sensor modalities. We introduce Filtered Multi- Modal Cross Attention Fusion (FMCAF), a preprocess- ing architecture designed to enhance the fusion of RGB and infrared (IR) inputs. FMCAF combines a frequency- domain filtering block (Freq-Filter) to suppress redun- dant spectral features with a cross-attention-based fusion module (MCAF) to improve intermodal feature sharing. Unlike approaches tailored to specific datasets, FMCAF aims for generalizability, improving performance across different multimodal challenges without requiring dataset- specific tuning. On LLVIP (low-light pedestrian detec- tion) and VEDAI (aerial vehicle detection), FMCAF outper- forms traditional fusion (concatenation), achieving +13.9% mAP@50 on VEDAI and +1.1% on LLVIP. These results support the potential of FMCAF as a flexible foundation for robust multimodal fusion in future detection pipelines.
@article{arxiv.2510.17078,
title = {Towards a Generalizable Fusion Architecture for Multimodal Object Detection},
author = {Jad Berjawi and Yoann Dupas and Christophe C'erin},
journal= {arXiv preprint arXiv:2510.17078},
year = {2025}
}
Comments
8 pages, 8 figures, accepted at ICCV 2025 MIRA Workshop