# Joint Supervised and Self-Supervised Learning for 3D Real-World Challenges

arXiv: https://arxiv.org/abs/2004.07392 · HTML: https://mlsanity.com/paper/2004.07392/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Apr 2020.

## Built on by (most cited first, 21 of 21)

- [PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models](https://mlsanity.com/paper/2212.01558/) (2022)
- [Domain Adaptation on Point Clouds via Geometry-Aware Implicits](https://mlsanity.com/paper/2112.09343/) (2021)
- [Self-Distillation for Unsupervised 3D Domain Adaptation](https://mlsanity.com/paper/2210.08226/) (2022)
- [3DOS: Towards 3D Open Set Learning -- Benchmarking and Understanding Semantic Novelty Detection on Point Clouds](https://mlsanity.com/paper/2207.11554/) (2022)
- [CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformation](https://mlsanity.com/paper/2407.16193/) (2024)
- [MvDeCor: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentation](https://mlsanity.com/paper/2208.08580/) (2022)
- [Anatomy-guided domain adaptation for 3D in-bed human pose estimation](https://mlsanity.com/paper/2211.12193/) (2022)
- [RefRec: Pseudo-labels Refinement via Shape Reconstruction for Unsupervised 3D Domain Adaptation](https://mlsanity.com/paper/2110.11036/) (2021)
- [Semi-supervised 3D shape segmentation with multilevel consistency and part substitution](https://mlsanity.com/paper/2204.08824/) (2022)
- [Self-Supervised Learning with Multi-View Rendering for 3D Point Cloud Analysis](https://mlsanity.com/paper/2210.15904/) (2022)
- [A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds](https://mlsanity.com/paper/2104.05164/) (2021)
- [PriFit: Learning to Fit Primitives Improves Few Shot Point Cloud Segmentation](https://mlsanity.com/paper/2112.13942/) (2021)
- [Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans](https://mlsanity.com/paper/2304.09704/) (2023)
- [LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectives](https://mlsanity.com/paper/2503.18384/) (2025)
- [Self-Supervision & Meta-Learning for One-Shot Unsupervised Cross-Domain Detection](https://mlsanity.com/paper/2106.03496/) (2021)
- [Self-Supervised Feature Learning from Partial Point Clouds via Pose Disentanglement](https://mlsanity.com/paper/2201.03018/) (2022)
- [Open-Set Semi-Supervised Learning for 3D Point Cloud Understanding](https://mlsanity.com/paper/2205.01006/) (2022)
- [PatchContrast: Self-Supervised Pre-training for 3D Object Detection](https://mlsanity.com/paper/2308.06985/) (2023)
- [Unsupervised Pre-Training for 3D Leaf Instance Segmentation](https://mlsanity.com/paper/2401.08720/) (2024)
- [To Supervise or Not to Supervise: Understanding and Addressing the Key Challenges of Point Cloud Transfer Learning](https://mlsanity.com/paper/2403.17869/) (2024)
- [Locating and Mitigating Gradient Conflicts in Point Cloud Domain Adaptation via Saliency Map Skewness](https://mlsanity.com/paper/2504.15796/) (2025)

## Abstract (arXiv)

Point cloud processing and 3D shape understanding are very challenging tasks for which deep learning techniques have demonstrated great potentials. Still further progresses are essential to allow artificial intelligent agents to interact with the real world, where the amount of annotated data may be limited and integrating new sources of knowledge becomes crucial to support autonomous learning. Here we consider several possible scenarios involving synthetic and real-world point clouds where supervised learning fails due to data scarcity and large domain gaps. We propose to enrich standard feature representations by leveraging self-supervision through a multi-task model that can solve a 3D puzzle while learning the main task of shape classification or part segmentation. An extensive analysis investigating few-shot, transfer learning and cross-domain settings shows the effectiveness of our approach with state-of-the-art results for 3D shape classification and part segmentation.