BROWSE
Detail
Journal Article
LGD-BEV: Label-Guided Distillation for BEV 3D Object Detection
- Authors
- Ji-Yong Lee, Minho Park, Youngjoo Jo, Dong-Oh Kang
- Issue Date
- 2025-10
- Citation
- IEEE Access, v.13, pp.181836-181845
- ISSN
- 2169-3536
- Publisher
- IEEE
- Language
- English
- Type
- Journal Article
- Abstract
- Knowledge distillation in autonomous driving typically involves transferring information from high-cost sensor modalities such as LiDAR to camera-based models to improve 3D object detection. However, these methods often require access to additional modalities during training or inference, leading to increased engineering complexity and extensive trial-and-error efforts. This limitation hinders their scalability and deployment in real-world applications. In contrast, our approach leverages only 3D ground-truth annotations as an auxiliary intermediate supervision, acting as a lightweight teacher and removing the dependency on external sensors or strong pre-trained teachers. In this paper, we introduce a Label Encoder module to generate dense semantic representations in the Bird’s-Eye View (BEV) space to guide the training of camera-based networks through knowledge distillation. Specifically, we train an AutoEncoder on 3D ground-truth annotations and use its encoder to produce informative BEV features, which are then used as an auxiliary loss for the camera-based detection backbone. This yields a lightweight, modality-independent, and scalable solution, as demonstrated through extensive evaluations on the nuScenes dataset.
- KSP Keywords
- 3D object detection, Ground Truth, Knowledge Distillation, Real-world applications, Semantic representations, Trial-and-error, autonomous driving, camera based
This work is distributed under the term of Creative Commons License (CCL)
(CC BY)
(CC BY)
