Pith. sign in

REVIEW 1 cited by

Pseudo-labeling for Scalable 3D Object Detection

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2103.02093 v1 pith:7C6FX3SQ submitted 2021-03-02 cs.CV cs.LG

classification cs.CVcs.LG
keywords modelsdatastudentbetterexpensivelabeledaccuracyacross
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

To safely deploy autonomous vehicles, onboard perception systems must work reliably at high accuracy across a diverse set of environments and geographies. One of the most common techniques to improve the efficacy of such systems in new domains involves collecting large labeled datasets, but such datasets can be extremely costly to obtain, especially if each new deployment geography requires additional data with expensive 3D bounding box annotations. We demonstrate that pseudo-labeling for 3D object detection is an effective way to exploit less expensive and more widely available unlabeled data, and can lead to performance gains across various architectures, data augmentation strategies, and sizes of the labeled dataset. Overall, we show that better teacher models lead to better student models, and that we can distill expensive teachers into efficient, simple students. Specifically, we demonstrate that pseudo-label-trained student models can outperform supervised models trained on 3-10 times the amount of labeled examples. Using PointPillars [24], a two-year-old architecture, as our student model, we are able to achieve state of the art accuracy simply by leveraging large quantities of pseudo-labeled data. Lastly, we show that these student models generalize better than supervised models to a new domain in which we only have unlabeled data, making pseudo-label training an effective form of unsupervised domain adaptation.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ZeroVO: Visual Odometry with Minimal Assumptions

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A two-frame visual odometry model using estimated depth, language priors, and semi-supervised pseudo-label filtering achieves zero-shot metric-scale pose estimation across multiple driving datasets.

Pith tools