MHF-Net: Multi-Modal Residual Fusion Object Detection Network Based on High-Frequency Gated Convolution
Bailin Chen, Bo Qian · 2026
Read MHF-Net: Multi-Modal Residual Fusion Object Detection Network Based on High-Frequency Gated Convolution by Bailin Chen, Bo Qian (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13611251.txt.
Description
Bailin Chen and Bo Qian built an object detection network in 2026. Bad weather degrades driving camera images. Partial occlusion also hides road objects. Their network fuses several sensor modes. A gated high-frequency design guides fusion. Residual fusion blocks blend those features deeply.
Attention paths highlight key feature information. A high-frequency module sharpens fine detail. Tests used a multi-modal driving dataset. Detection precision reached high levels. Average precision also beat the baseline. Parameter count fell very sharply. Computing cost fell sharply too. The authors claim a good performance balance. Self-driving perception is the target use.
Catalog record
| CREATOR | Bailin Chen, Bo Qian |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 46 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |