3DResT: A Strong Baseline for Semi-Supervised 3D Referring Expression Segmentation
- URL: http://arxiv.org/abs/2504.12599v1
- Date: Thu, 17 Apr 2025 02:50:52 GMT
- Title: 3DResT: A Strong Baseline for Semi-Supervised 3D Referring Expression Segmentation
- Authors: Wenxin Chen, Mengxue Qu, Weitai Kang, Yan Yan, Yao Zhao, Yunchao Wei,
- Abstract summary: 3D Referring Expression (3D-RES) typically requires extensive instance-level annotations, which are time-consuming and costly.<n>Semi-supervised learning (SSL) mitigates this by using limited labeled data alongside abundant unlabeled data, improving performance while reducing annotation costs.<n>In this paper, we introduce the first semi-supervised learning framework for 3D-RES, presenting a robust baseline method named 3DResT.
- Score: 73.877177695218
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 3D Referring Expression Segmentation (3D-RES) typically requires extensive instance-level annotations, which are time-consuming and costly. Semi-supervised learning (SSL) mitigates this by using limited labeled data alongside abundant unlabeled data, improving performance while reducing annotation costs. SSL uses a teacher-student paradigm where teacher generates high-confidence-filtered pseudo-labels to guide student. However, in the context of 3D-RES, where each label corresponds to a single mask and labeled data is scarce, existing SSL methods treat high-quality pseudo-labels merely as auxiliary supervision, which limits the model's learning potential. The reliance on high-confidence thresholds for filtering often results in potentially valuable pseudo-labels being discarded, restricting the model's ability to leverage the abundant unlabeled data. Therefore, we identify two critical challenges in semi-supervised 3D-RES, namely, inefficient utilization of high-quality pseudo-labels and wastage of useful information from low-quality pseudo-labels. In this paper, we introduce the first semi-supervised learning framework for 3D-RES, presenting a robust baseline method named 3DResT. To address these challenges, we propose two novel designs called Teacher-Student Consistency-Based Sampling (TSCS) and Quality-Driven Dynamic Weighting (QDW). TSCS aids in the selection of high-quality pseudo-labels, integrating them into the labeled dataset to strengthen the labeled supervision signals. QDW preserves low-quality pseudo-labels by dynamically assigning them lower weights, allowing for the effective extraction of useful information rather than discarding them. Extensive experiments conducted on the widely used benchmark demonstrate the effectiveness of our method. Notably, with only 1% labeled data, 3DResT achieves an mIoU improvement of 8.34 points compared to the fully supervised method.
Related papers
- Co-Training with Active Contrastive Learning and Meta-Pseudo-Labeling on 2D Projections for Deep Semi-Supervised Learning [42.56511266791916]
SSL tackles this challenge by capitalizing on scarce labeled and abundant unlabeled data.
We present active-DeepFA, a method that effectively combines CL, teacher-student-based meta-pseudo-labeling and AL.
arXiv Detail & Related papers (2025-04-25T19:41:45Z) - DyConfidMatch: Dynamic Thresholding and Re-sampling for 3D Semi-supervised Learning [4.259908158892314]
Semi-supervised learning (SSL) leverages limited labeled and abundant unlabeled data but often faces challenges with data imbalance.
This study investigates class-level confidence as an indicator of learning status in 3D SSL, proposing a novel method that utilizes dynamic thresholding.
A re-sampling strategy is also introduced to mitigate bias towards well-represented classes, ensuring equitable class representation.
arXiv Detail & Related papers (2024-11-13T05:09:28Z) - TrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detection [59.498894868956306]
Pseudo-labeling approaches to semi-supervised learning adopt a teacher-student framework.
We leverage pre-trained motion-forecasting models to generate object trajectories on pseudo-labeled data.
Our approach improves pseudo-label quality in two distinct manners.
arXiv Detail & Related papers (2024-09-17T05:35:00Z) - Dual-Perspective Knowledge Enrichment for Semi-Supervised 3D Object
Detection [55.210991151015534]
We present a novel Dual-Perspective Knowledge Enrichment approach named DPKE for semi-supervised 3D object detection.
Our DPKE enriches the knowledge of limited training data, particularly unlabeled data, from two perspectives: data-perspective and feature-perspective.
arXiv Detail & Related papers (2024-01-10T08:56:07Z) - All Points Matter: Entropy-Regularized Distribution Alignment for
Weakly-supervised 3D Segmentation [67.30502812804271]
Pseudo-labels are widely employed in weakly supervised 3D segmentation tasks where only sparse ground-truth labels are available for learning.
We propose a novel learning strategy to regularize the generated pseudo-labels and effectively narrow the gaps between pseudo-labels and model predictions.
arXiv Detail & Related papers (2023-05-25T08:19:31Z) - Hierarchical Supervision and Shuffle Data Augmentation for 3D
Semi-Supervised Object Detection [90.32180043449263]
State-of-the-art 3D object detectors are usually trained on large-scale datasets with high-quality 3D annotations.
A natural remedy is to adopt semi-supervised learning (SSL) by leveraging a limited amount of labeled samples and abundant unlabeled samples.
This paper introduces a novel approach of Hierarchical Supervision and Shuffle Data Augmentation (HSSDA), which is a simple yet effective teacher-student framework.
arXiv Detail & Related papers (2023-04-04T02:09:32Z) - Teachers in concordance for pseudo-labeling of 3D sequential data [1.1610573589377013]
We propose to leverage sequences of point clouds to boost the pseudolabeling technique in a teacher-student setup via training multiple teachers.
This set of teachers, dubbed Concordance, provides higher quality pseudo-labels for student training than standard methods.
Our approach, which uses only 20% manual labels, outperforms some fully supervised methods.
arXiv Detail & Related papers (2022-07-13T09:40:22Z) - Open-Set Semi-Supervised Learning for 3D Point Cloud Understanding [62.17020485045456]
It is commonly assumed in semi-supervised learning (SSL) that the unlabeled data are drawn from the same distribution as that of the labeled ones.
We propose to selectively utilize unlabeled data through sample weighting, so that only conducive unlabeled data would be prioritized.
arXiv Detail & Related papers (2022-05-02T16:09:17Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.