paper-with-me

홈 › Papers

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

2022-03-17 · Jinhyung Park, Chenfeng Xu, Yiyang Zhou, Masayoshi Tomizuka, Wei Zhan

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

📄 PDF Abstract BibTeX arXiv:2203.09510

Code (1)

divadi/detmatch 공식 구현 pytorch

Tasks

object-detectionObject DetectionObject RecognitionSemi-Supervised Object Detection

Similar Papers 제목 키워드 기반

JEDI: Joint Expert Distillation in a Semi-Supervised Multi-Dataset Student-Teacher Scenario for Video Action Recognition

2023-08-09 · Lucian Bicsi, Bogdan Alexe, Radu Tudor Ionescu, Marius Leordeanu

We propose JEDI, a multi-dataset semi-supervised learning method, which efficiently combines knowledge from multiple experts, learned on different datasets, to train and improve the performance of individual, per dataset…

Action RecognitionTemporal Action Localization

Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data

2016-10-18 · Nicolas Papernot, Martín Abadi, Úlfar Erlingsson, Ian Goodfellow 외

Some machine learning applications involve training data that is sensitive, such as the medical histories of patients in a clinical trial. A model may inadvertently and implicitly store some of its training data; careful…

Transfer Learning

Representation Consolidation from Multiple Expert Teachers

2021-09-29 · Zhizhong Li, Avinash Ravichandran, Charless Fowlkes, Marzia Polito 외

A library of diverse expert models transfers better to a novel task than a single generalist model. However, growing such a library indefinitely is impractical. Hence, we explore the problem of learning a consolidated im…

Knowledge Distillation

Switching Temporary Teachers for Semi-Supervised Semantic Segmentation

2023-09-21 · NeurIPS 2023 11

The teacher-student framework, prevalent in semi-supervised semantic segmentation, mainly employs the exponential moving average (EMA) to update a single teacher's weights based on the student's. However, EMA updates rai…

Semi-Supervised Semantic Segmentation

Humble Teachers Teach Better Students for Semi-Supervised Object Detection

2021-06-19 · CVPR 2021 1 · Yihe Tang, Weifeng Chen, Yijun Luo, Yuting Zhang

We propose a semi-supervised approach for contemporary object detectors following the teacher-student dual model framework. Our method is featured with 1) the exponential moving averaging strategy to update the teacher f…

object-detectionObject DetectionSemi-Supervised Object Detection