Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2510.17078 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909857088536576 |
|---|---|
| author | Berjawi, Jad Dupas, Yoann C'erin, Christophe |
| author_facet | Berjawi, Jad Dupas, Yoann C'erin, Christophe |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_17078 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards a Generalizable Fusion Architecture for Multimodal Object Detection Berjawi, Jad Dupas, Yoann C'erin, Christophe Computer Vision and Pattern Recognition I.2.10; I.4.8 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. |
| title | Towards a Generalizable Fusion Architecture for Multimodal Object Detection |
| topic | Computer Vision and Pattern Recognition I.2.10; I.4.8 |
| url | https://arxiv.org/abs/2510.17078 |