Breaking the SSL-AL Barrier: A Synergistic Semi-Supervised Active Learning Framework for 3D Object Detection

TL;DR

This paper introduces a novel framework called S-SSAL that combines semi-supervised learning and active learning to significantly reduce annotation efforts in 3D object detection, achieving high performance with minimal labeled data.

Contribution

The paper proposes a synergistic framework integrating semi-supervised and active learning for 3D detection, including a new pre-training method and a model cascading active learning strategy.

Findings

Achieves comparable performance with only 2% labeled data on KITTI.

Demonstrates effectiveness on KITTI and Waymo datasets.

Outperforms traditional active learning methods in 3D detection tasks.

Abstract

To address the annotation burden in LiDAR-based 3D object detection, active learning (AL) methods offer a promising solution. However, traditional active learning approaches solely rely on a small amount of labeled data to train an initial model for data selection, overlooking the potential of leveraging the abundance of unlabeled data. Recently, attempts to integrate semi-supervised learning (SSL) into AL with the goal of leveraging unlabeled data have faced challenges in effectively resolving the conflict between the two paradigms, resulting in less satisfactory performance. To tackle this conflict, we propose a Synergistic Semi-Supervised Active Learning framework, dubbed as S-SSAL. Specifically, from the perspective of SSL, we propose a Collaborative PseudoScene Pre-training (CPSP) method that effectively learns from unlabeled data without introducing adverse effects. From the perspective of AL, we design a Collaborative Active Learning (CAL) method, which complements the uncertainty and diversity methods by model cascading. This allows us to fully exploit the potential of the CPSP pre-trained model. Extensive experiments conducted on KITTI and Waymo demonstrate the effectiveness of our S-SSAL framework. Notably, on the KITTI dataset, utilizing only 2% labeled data, S-SSAL can achieve performance comparable to models trained on the full dataset. The code has been released at https://github.com/LandDreamer/S_SSAL.