Work

Region-aware knowledge distillation between monocular camera-based 3D object detectors

Year: 2025

Type: article

Abstract: Recent knowledge distillation (KD) for 3D object detection often involves costly LiDAR or multi-camera data. We focus on monocular camera-based 3D detectors, where missing 3D cues cause large feature gaps. To address this, we propose region-aware KD, aligning object features by matching their scales and pyramid levels. We introduce a probabilistic distribution to weigh region importance. Applied to MonoRCNN++ and MonoDETR on the KITTI and Waymo dataset, our approach achieves reduced complexity and strong performance with a lightweight backbone. Compared to recent KD methods, ours excels in both effectiveness and efficiency.

Source: ICT Express

DOI: 10.1016/j.icte.2025.04.012

Authors: Se-Gwon Cheon, Hyuk-Jin Shin, Seung-Hwan Bae

Institution: Inha University

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,500

Funder: Inha University