Butter: Frequency Consistency and Hierarchical Fusion for Autonomous Driving Object Detection

TL;DR

Butter is a novel object detection framework for autonomous driving that enhances hierarchical feature consistency and fusion, leading to improved accuracy and efficiency in detecting pedestrians, vehicles, and traffic signs.

Contribution

It introduces FAFCE and PHFFNet modules to refine multi-scale features and integrate hierarchical information, addressing feature inconsistency and semantic gaps in existing detectors.

Findings

Outperforms existing methods on BDD100K, KITTI, and Cityscapes datasets.

Improves detection accuracy while reducing model complexity.

Achieves a balance between robustness and computational efficiency.

Abstract

Hierarchical feature representations play a pivotal role in computer vision, particularly in object detection for autonomous driving. Multi-level semantic understanding is crucial for accurately identifying pedestrians, vehicles, and traffic signs in dynamic environments. However, existing architectures, such as YOLO and DETR, struggle to maintain feature consistency across different scales while balancing detection precision and computational efficiency. To address these challenges, we propose Butter, a novel object detection framework designed to enhance hierarchical feature representations for improving detection robustness. Specifically, Butter introduces two key innovations: Frequency-Adaptive Feature Consistency Enhancement (FAFCE) Component, which refines multi-scale feature consistency by leveraging adaptive frequency filtering to enhance structural and boundary precision, and Progressive Hierarchical Feature Fusion Network (PHFFNet) Module, which progressively integrates multi-level features to mitigate semantic gaps and strengthen hierarchical feature learning. Through extensive experiments on BDD100K, KITTI, and Cityscapes, Butter demonstrates superior feature representation capabilities, leading to notable improvements in detection accuracy while reducing model complexity. By focusing on hierarchical feature refinement and integration, Butter provides an advanced approach to object detection that achieves a balance between accuracy, deployability, and computational efficiency in real-time autonomous driving scenarios. Our model and implementation are publicly available at https://github.com/Aveiro-Lin/Butter, facilitating further research and validation within the autonomous driving community.