3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection

Wang, He; Cong, Yezhen; Litany, Or; Gao, Yue; Guibas, Leonidas J.

doi:10.1109/cvpr46437.2021.01438

Cited by 75 publications

(63 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach has been applied in many domains, such as semi-supervised learning (SSL) [2,3,36,50], unsupervised learning (USL) [8,12], unsupervised domain adaptation (UDA) [6,35], and semi-supervised domain adaptation (SSDA) [21,22], all of which prove the effectiveness of consistency training in learning high-quality representations from label-scarce data. More recently, there are some works extending consistency training into other tasks, such as unsupervised domain adaptation for image segmentation [27] and semi-supervised 3D object detection [43].…”

Section: Related Workmentioning

confidence: 99%

PointMatch: A Consistency Training Framework for Weakly Supervised Semantic Segmentation of 3D Point Clouds

Wu¹,

Yan²,

Cai³

et al. 2022

Preprint

View full text Add to dashboard Cite

Semantic segmentation of point cloud usually relies on dense annotation that is exhausting and costly, so it attracts wide attention to investigate solutions for the weakly supervised scheme with only sparse points annotated. Existing works start from the given labels and propagate them to highly-related but unlabeled points, with the guidance of data, e.g. intra-point relation. However, it suffers from (i) the inefficient exploitation of data information, and (ii) the strong reliance on labels thus is easily suppressed when given much fewer annotations. Therefore, we propose a novel framework, PointMatch, that stands on both data and label, by applying consistency regularization to sufficiently probe information from data itself and leveraging weak labels as assistance at the same time. By doing so, meaningful information can be learned from both data and label for better representation learning, which also enables the model more robust to the extent of label sparsity. Simple yet effective, the proposed PointMatch achieves the state-of-theart performance under various weakly-supervised schemes on both ScanNet-v2 and S3DIS datasets, especially on the settings with extremely sparse labels, e.g. surpassing SQN by 21.2% and 17.2% on the 0.01% and 0.1% setting of ScanNet-v2, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

PointMatch: A Consistency Training Framework for Weakly Supervised Semantic Segmentation of 3D Point Clouds

Wu¹,

Yan²,

Cai³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…which often makes incorrect predictions. Another promising direction for SSL is self-ensembling, which encourages consensus among ensemble predictions of unknown samples under small perturbations of inputs or network parameters [40,17,28]. The student learns to perform better than the teacher due to its robustness to corruption.…”

Section: D Video Object Detectionmentioning

confidence: 99%

Semi-supervised 3D Object Detection via Temporal Graph Neural Networks

Wang¹,

Gang²,

Siddarth³

et al. 2022

Preprint

View full text Add to dashboard Cite

3D object detection plays an important role in autonomous driving and other robotics applications. However, these detectors usually require training on large amounts of annotated data that is expensive and timeconsuming to collect. Instead, we propose leveraging large amounts of unlabeled point cloud videos by semi-supervised learning of 3D object detectors via temporal graph neural networks. Our insight is that temporal smoothing can create more accurate detection results on unlabeled data, and these smoothed detections can then be used to retrain the detector. We learn to perform this temporal reasoning with a graph neural network, where edges represent the relationship between candidate detections in different time frames. After semi-supervised learning, our method achieves state-of-the-art detection performance on the challenging nuScenes [3] and H3D [19] benchmarks, compared to baselines trained on the same amount of labeled data. Project and code are released at https: //www.jianrenw.com/SOD-TGNN/.

show abstract

“…1) Semi Supervision: Research on semi-supervised learning has mostly been conducted on the image classification setting [12], [13], [14], [15], [16], [17], [13], [18], [19], [20], [21], with interest in segmentation and object detection only rising recently [22], [23], [24], [25], [26], [27], [28], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39]. We follow these last set of works and characterize the semi supervision setting as: (upon sorting,) for a certain integer S, full labels are provided for images with indices 1 ≤ i ≤ S, and no labels for images with indices S < i ≤ M.…”

Section: B Partial Supervisionmentioning

confidence: 99%

Multi-Class 3D Object Detection with Single-Class Supervision

Ye¹,

Liu²,

Yao³

et al. 2022

Preprint

View full text Add to dashboard Cite

While multi-class 3D detectors are needed in many robotics applications, training them with fully labeled datasets can be expensive in labeling cost. An alternative approach is to have targeted single-class labels on disjoint data samples. In this paper, we are interested in training a multi-class 3D object detection model, while using these single-class labeled data. We begin by detailing the unique stance of our "Single-Class Supervision" (SCS) setting with respect to related concepts such as partial supervision and semi supervision. Then, based on the case study of training the multi-class version of Range Sparse Net (RSN), we adapt a spectrum of algorithms -from supervised learning to pseudolabeling -to fully exploit the properties of our SCS setting, and perform extensive ablation studies to identify the most effective algorithm and practice. Empirical experiments on the Waymo Open Dataset show that proper training under SCS can approach or match full supervision training while saving labeling costs.

show abstract

3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection

Cited by 75 publications

References 14 publications

PointMatch: A Consistency Training Framework for Weakly Supervised Semantic Segmentation of 3D Point Clouds

PointMatch: A Consistency Training Framework for Weakly Supervised Semantic Segmentation of 3D Point Clouds

Semi-supervised 3D Object Detection via Temporal Graph Neural Networks

Multi-Class 3D Object Detection with Single-Class Supervision

Contact Info

Product

Resources

About