Butter: Frequency Consistency and Hierarchical Fusion for Autonomous Driving Object Detection
Paper
•
2507.13373
•
Published
Model Card for Model ID
Butter is a novel 2D object detection framework designed to enhance hierarchical feature representations for improved detection robustness.
Model Details
Model Description
- Developed by: [Xiaojian Lin et al.]
- Funded by: [National Natural Science Foundation of China]
- Model type: [Object Detection]
- License: [AGPL-3.0 license]
Model Sources [optional]
- Repository: [https://github.com/Aveiro-Lin/Butter]
- Paper: [https://www.arxiv.org/pdf/2507.13373]
Uses
The training and inference details, as well as the environment configuration, can be found in our GitHub repository, where a comprehensive description is provided. The model’s performance metrics and training details are thoroughly described in the paper we provide.