# 3DResT: A Strong Baseline for Semi-Supervised 3D Referring Expression Segmentation

arXiv: https://arxiv.org/abs/2504.12599 · HTML: https://mlsanity.com/paper/2504.12599/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 46 of its 65 references that are in the map.
- First posted on arXiv 17 Apr 2025.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 30 of 46)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://mlsanity.com/paper/1711.09869/) (2017)
- [ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring](https://mlsanity.com/paper/1911.09785/) (2019)
- [Learning with Pseudo-Ensembles](https://mlsanity.com/paper/1412.4864/) (2014)
- [Multi3DRefer: Grounding Text Description to Multiple 3D Objects](https://mlsanity.com/paper/2309.05251/) (2023)
- [Language Conditioned Spatial Relation Reasoning for 3D Object Grounding](https://mlsanity.com/paper/2211.09646/) (2022)
- [Superpoint Transformer for 3D Scene Instance Segmentation](https://mlsanity.com/paper/2211.15766/) (2022)
- [LaserMix for Semi-Supervised LiDAR Semantic Segmentation](https://mlsanity.com/paper/2207.00026/) (2022)
- [SESS: Self-Ensembling Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/1912.11803/) (2019)
- [Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2110.08188/) (2021)
- [Multiple instance active learning for object detection](https://mlsanity.com/paper/2104.02324/) (2021)
- [Attentive Relational Networks for Mapping Images to Scene Graphs](https://mlsanity.com/paper/1811.10696/) (2018)
- [Efficient 3D Semantic Segmentation with Superpoint Transformer](https://mlsanity.com/paper/2306.08045/) (2023)
- [SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network](https://mlsanity.com/paper/2104.07861/) (2021)
- [Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection](https://mlsanity.com/paper/2103.16368/) (2021)
- [Active Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2303.08348/) (2023)
- [3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation](https://mlsanity.com/paper/2308.16632/) (2023)
- [SegPoint: Segment Any Point Cloud via Large Language Model](https://mlsanity.com/paper/2407.13761/) (2024)
- [LIF-Seg: LiDAR and Camera Image Fusion for 3D LiDAR Semantic Segmentation](https://mlsanity.com/paper/2108.07511/) (2021)
- [Consistency-based Active Learning for Object Detection](https://mlsanity.com/paper/2103.10374/) (2021)
- [Global-Local Tree Search in VLMs for 3D Indoor Scene Generation](https://mlsanity.com/paper/2503.18476/) (2025)
- [SGFormer: Semantic Graph Transformer for Point Cloud-based 3D Scene Graph Generation](https://mlsanity.com/paper/2303.11048/) (2023)
- [Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning](https://mlsanity.com/paper/2410.00255/) (2024)
- [RefMask3D: Language-Guided Transformer for 3D Referring Segmentation](https://mlsanity.com/paper/2407.18244/) (2024)

## Built on by (most cited first, 2 of 2)

- [Multimodal Referring Segmentation: A Survey](https://mlsanity.com/paper/2508.00265/) (2025)
- [MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation](https://mlsanity.com/paper/2601.06874/) (2026)

## Abstract (arXiv)

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.