透過分佈差異和特徵異質性進行主動 3D 物體偵測

Abstract

基於光學雷達的3D物體檢測是自動駕駛和機器人發展的關鍵技術。然而，資料標註的成本過高限制了其發展。我們提出一種新穎且有效的主動學習方法，名為分布差異與特徵異質性（DDFH），該方法同時考慮幾何特徵和模型嵌入，從實例層面和框架層面評估信息。分布差異評估未標記和已標記分布中實例的差異性和新穎性，使模型能夠在有限的數據下高效學習。特徵異質性確保框架內實例特徵的異質性，保持特徵多樣性，同時避免冗餘或相似實例，從而最小化標註成本。最後，使用分位數變換有效地聚合多個指標，提供一個統一的資訊量指標。廣泛的實驗表明，DDFH在KITTI和Waymo數據集上超越了當前最先進（SOTA）方法，有效地減少了標定框標註成本56.3％，並在單階段和雙階段的模型中展現出穩健性。

LiDAR-based 3D object detection is a critical technology for the development of autonomous driving and robotics. However, the high cost of data annotation limits its advancement. We propose a novel and effective active learning (AL) method called Distribution Discrepancy and Feature Heterogeneity (DDFH), which simultaneously considers geometric features and model embeddings, assessing information from both the instance-level and frame-level perspectives. Distribution Discrepancy evaluates the difference and novelty of instances within the unlabeled and labeled distributions, enabling the model to learn efficiently with limited data. Feature Heterogeneity ensures the heterogeneity of intra-frame instance features, maintaining feature diversity while avoiding redundant or similar instances, thus minimizing annotation costs. Finally, multiple indicators are efficiently aggregated using Quantile Transform, providing a unified measure of informativeness. Extensive experiments demonstrate that DDFH outperforms the current state-of-the-art (SOTA) methods on the KITTI and Waymo datasets, effectively reducing the bounding box annotation cost by 56.3% and showing robustness when working with both one-stage and two-stage models.