# Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition

arXiv: https://arxiv.org/abs/2308.09694 · HTML: https://mlsanity.com/paper/2308.09694/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 81 references that are in the map.
- First posted on arXiv 18 Aug 2023.

## Builds on (most cited first, 30 of 56)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data](https://mlsanity.com/paper/1908.04616/) (2019)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [Masked Autoencoders for Point Cloud Self-supervised Learning](https://mlsanity.com/paper/2203.06604/) (2022)
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)

## Built on by (most cited first, 13 of 13)

- [View-Consistent 3D Editing with Gaussian Splatting](https://mlsanity.com/paper/2403.11868/) (2024)
- [Consistent3D: Towards Consistent High-Fidelity Text-to-3D Generation with Deterministic Sampling Prior](https://mlsanity.com/paper/2401.09050/) (2024)
- [Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction](https://mlsanity.com/paper/2403.18795/) (2024)
- [Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models](https://mlsanity.com/paper/2310.08106/) (2023)
- [HumanEdit: A High-Quality Human-Rewarded Dataset for Instruction-based Image Editing](https://mlsanity.com/paper/2412.04280/) (2024)
- [Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting](https://mlsanity.com/paper/2410.19294/) (2024)
- [MVGamba: Unify 3D Content Generation as State Space Sequence Modeling](https://mlsanity.com/paper/2406.06367/) (2024)
- [It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition](https://mlsanity.com/paper/2402.05457/) (2024)
- [Diffusion Time-step Curriculum for One Image to 3D Generation](https://mlsanity.com/paper/2404.04562/) (2024)
- [Integrating View Conditions for Image Synthesis](https://mlsanity.com/paper/2310.16002/) (2023)
- [Seeing World Dynamics in a Nutshell](https://mlsanity.com/paper/2502.03465/) (2025)
- [Formula-Supervised Visual-Geometric Pre-training](https://mlsanity.com/paper/2409.13535/) (2024)
- [Efficient 3D Perception on Multi-Sweep Point Cloud with Gumbel Spatial Pruning](https://mlsanity.com/paper/2411.07742/) (2024)

## Abstract (arXiv)

We tackle the data scarcity challenge in few-shot point cloud recognition of 3D objects by using a joint prediction from a conventional 3D model and a well-trained 2D model. Surprisingly, such an ensemble, though seems trivial, has hardly been shown effective in recent 2D-3D models. We find out the crux is the less effective training for the ''joint hard samples'', which have high confidence prediction on different wrong labels, implying that the 2D and 3D models do not collaborate well. To this end, our proposed invariant training strategy, called InvJoint, does not only emphasize the training more on the hard samples, but also seeks the invariance between the conflicting 2D and 3D ambiguous predictions. InvJoint can learn more collaborative 2D and 3D representations for better ensemble. Extensive experiments on 3D shape classification with widely adopted ModelNet10/40, ScanObjectNN and Toys4K, and shape retrieval with ShapeNet-Core validate the superiority of our InvJoint.