# Transductive Zero-Shot Learning for 3D Point Cloud Classification

arXiv: https://arxiv.org/abs/1912.07161 · HTML: https://mlsanity.com/paper/1912.07161/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Dec 2019.

## Built on by (most cited first, 30 of 39)

- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [PLA: Language-Driven Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2211.16312/) (2022)
- [Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2103.04059/) (2021)
- [RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding](https://mlsanity.com/paper/2304.00962/) (2023)
- [CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP](https://mlsanity.com/paper/2303.04748/) (2023)
- [CLIP2: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data](https://mlsanity.com/paper/2303.12417/) (2023)
- [Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2108.06230/) (2021)
- [Open-Vocabulary Affordance Detection in 3D Point Clouds](https://mlsanity.com/paper/2303.02401/) (2023)
- [Zero-Shot Learning on 3D Point Cloud Objects and Beyond](https://mlsanity.com/paper/2104.04980/) (2021)
- [Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding](https://mlsanity.com/paper/2308.00353/) (2023)
- [Zero-Shot 3D Shape Correspondence](https://mlsanity.com/paper/2306.03253/) (2023)
- [3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds](https://mlsanity.com/paper/2502.20041/) (2025)
- [OpenSight: A Simple Open-Vocabulary Framework for LiDAR-Based Object Detection](https://mlsanity.com/paper/2312.08876/) (2023)
- [See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data](https://mlsanity.com/paper/2307.10782/) (2023)
- [A Survey of Label-Efficient Deep Learning for 3D Point Clouds](https://mlsanity.com/paper/2305.19812/) (2023)
- [3D Compositional Zero-shot Learning with DeCompositional Consensus](https://mlsanity.com/paper/2111.14673/) (2021)
- [UniM-OV3D: Uni-Modality Open-Vocabulary 3D Scene Understanding with Fine-Grained Feature Representation](https://mlsanity.com/paper/2401.11395/) (2024)
- [Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2407.13642/) (2024)
- [A Closer Look at Few-Shot 3D Point Cloud Classification](https://mlsanity.com/paper/2303.18210/) (2023)
- [Zero-shot point cloud segmentation by transferring geometric primitives](https://mlsanity.com/paper/2210.09923/) (2022)
- [Towards Zero-shot 3D Anomaly Localization](https://mlsanity.com/paper/2412.04304/) (2024)
- [Language-Level Semantics Conditioned 3D Point Cloud Segmentation](https://mlsanity.com/paper/2107.00430/) (2021)
- [What Makes for Effective Few-shot Point Cloud Classification?](https://mlsanity.com/paper/2304.00022/) (2023)
- [Multi-Label Generalized Zero Shot Learning for the Classification of Disease in Chest Radiographs](https://mlsanity.com/paper/2107.06563/) (2021)
- [Robotic-CLIP: Fine-tuning CLIP on Action Data for Robotic Applications](https://mlsanity.com/paper/2409.17727/) (2024)
- [Deep Point Cloud Normal Estimation via Triplet Learning](https://mlsanity.com/paper/2110.10494/) (2021)
- [Open-Pose 3D Zero-Shot Learning: Benchmark and Challenges](https://mlsanity.com/paper/2312.07039/) (2023)
- [Continual Learning in 3D Point Clouds: Employing Spectral Techniques for Exemplar Selection](https://mlsanity.com/paper/2409.08388/) (2024)
- [PGOV3D: Open-Vocabulary 3D Semantic Segmentation with Partial-to-Global Curriculum](https://mlsanity.com/paper/2506.23607/) (2025)
- ["Zero-Shot" Point Cloud Upsampling](https://mlsanity.com/paper/2106.13765/) (2021)

## Abstract (arXiv)

Zero-shot learning, the task of learning to recognize new classes not seen during training, has received considerable attention in the case of 2D image classification. However despite the increasing ubiquity of 3D sensors, the corresponding 3D point cloud classification problem has not been meaningfully explored and introduces new challenges. This paper extends, for the first time, transductive Zero-Shot Learning (ZSL) and Generalized Zero-Shot Learning (GZSL) approaches to the domain of 3D point cloud classification. To this end, a novel triplet loss is developed that takes advantage of unlabeled test data. While designed for the task of 3D point cloud classification, the method is also shown to be applicable to the more common use-case of 2D image classification. An extensive set of experiments is carried out, establishing state-of-the-art for ZSL and GZSL in the 3D point cloud domain, as well as demonstrating the applicability of the approach to the image domain.