UpCycling: Semi-supervised 3D Object Detection without Sharing Raw-level Unlabeled Scenes

TL;DR

UpCycling introduces a semi-supervised 3D object detection framework that leverages unlabeled intermediate features to enhance detection accuracy while preserving privacy, without requiring raw point cloud data.

Contribution

The paper presents a novel SSL framework using unlabeled intermediate features and a hybrid pseudo label strategy, avoiding raw data sharing and improving detection performance.

Findings

Outperforms other feature-level augmentation methods on multiple datasets.

Achieves comparable or better results than raw-data-based SSL methods.

Preserves privacy by not sharing raw point cloud data.

Abstract

Semi-supervised Learning (SSL) has received increasing attention in autonomous driving to reduce the enormous burden of 3D annotation. In this paper, we propose UpCycling, a novel SSL framework for 3D object detection with zero additional raw-level point cloud: learning from unlabeled de-identified intermediate features (i.e., smashed data) to preserve privacy. Since these intermediate features are naturally produced by the inference pipeline, no additional computation is required on autonomous vehicles. However, generating effective consistency loss for unlabeled feature-level scene turns out to be a critical challenge. The latest SSL frameworks for 3D object detection that enforce consistency regularization between different augmentations of an unlabeled raw-point scene become detrimental when applied to intermediate features. To solve the problem, we introduce a novel combination of hybrid pseudo labels and feature-level Ground Truth sampling (F-GT), which safely augments unlabeled multi-type 3D scene features and provides high-quality supervision. We implement UpCycling on two representative 3D object detection models: SECOND-IoU and PV-RCNN. Experiments on widely-used datasets (Waymo, KITTI, and Lyft) verify that UpCycling outperforms other augmentation methods applied at the feature level. In addition, while preserving privacy, UpCycling performs better or comparably to the state-of-the-art methods that utilize raw-level unlabeled data in both domain adaptation and partial-label scenarios.