# DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection

Source: [DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection](<https://www.sota2.com/research/paper/68fa6c111e209131cea31df7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:52.408Z

Authors: Jinhyung Park, Chenfeng Xu, Yiyang Zhou, Masayoshi Tomizuka, Wei Zhan

Published: 2022-03-17T17:58:00.000Z

## Abstract

While numerous 3D detection works leverage the complementary relationship between RGB images and point clouds, developments in the broader framework of semi-supervised object recognition remain uninfluenced by multi-modal fusion. Current methods develop independent pipelines for 2D and 3D semi-supervised learning despite the availability of paired image and point cloud frames. Observing that the distinct characteristics of each sensor cause them to be biased towards detecting different objects, we propose DetMatch, a flexible framework for joint semi-supervised learning on 2D and 3D modalities. By identifying objects detected in both sensors, our pipeline generates a cleaner, more robust set of pseudo-labels that both demonstrates stronger performance and stymies single-modality error propagation. Further, we leverage the richer semantics of RGB images to rectify incorrect 3D class predictions and improve localization of 3D boxes. Evaluating on the challenging KITTI and Waymo datasets, we improve upon strong semi-supervised learning methods and observe higher quality pseudo-labels. Code will be released at https://github.com/Divadi/DetMatch

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Object Detection on KITTI 1% (val)](<https://www.sota2.com/research/sota/3d-object-detection-on-kitti-1-percent-val.md>): 3D Object Detection; KITTI 1% (val); AP (Car): 77.5.

- [3D Object Detection on Waymo 1% label (val)](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-1-percent-label-val.md>): 3D Object Detection; Waymo 1% label (val); Vehicle (L1) AP: 52.2.

- [3D Object Detection on KITTI (2% val)](<https://www.sota2.com/research/sota/3d-object-detection-on-kitti-2-percent-val.md>): 3D Object Detection; KITTI (2% val); Car AP: 78.2.

- [3D Object Detection on Waymo Open Dataset (val)](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-dataset-val.md>): 3D Object Detection; Waymo Open Dataset (val); 3D APH Vehicle L2: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2203.09510>)

[PDF](<https://arxiv.org/pdf/2203.09510.pdf>)