# Generalized Zero-Shot Learning for Point Cloud Segmentation with Evidence-Based Dynamic Calibration

arXiv: https://arxiv.org/abs/2509.08280 · HTML: https://mlsanity.com/paper/2509.08280/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 10 Sep 2025.

## Builds on (most cited first, 21 of 21)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data](https://mlsanity.com/paper/1908.04616/) (2019)
- [Generative Moment Matching Networks](https://mlsanity.com/paper/1502.02761/) (2015)
- [An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild](https://mlsanity.com/paper/1605.04253/) (2016)
- [Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation](https://mlsanity.com/paper/2110.03051/) (2021)
- [ConvPoint: Continuous Convolutions for Point Cloud Processing](https://mlsanity.com/paper/1904.02375/) (2019)
- [Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2108.06230/) (2021)
- [Zero-Shot Learning on 3D Point Cloud Objects and Beyond](https://mlsanity.com/paper/2104.04980/) (2021)
- [Zero-shot Learning of 3D Point Cloud Objects](https://mlsanity.com/paper/1902.10272/) (2019)
- [A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2008.04872/) (2020)
- [Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects](https://mlsanity.com/paper/1907.06371/) (2019)
- [See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data](https://mlsanity.com/paper/2307.10782/) (2023)
- [Model Selection for Generalized Zero-shot Learning](https://mlsanity.com/paper/1811.03252/) (2018)

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

- [Estimating Uncertainty in Galaxy Morphology Classification](https://mlsanity.com/paper/2608.08398/) (2026)
- [Learning from Multimodal Pseudo-Labels for Robust Open-Vocabulary Instance and Panoptic Segmentation](https://mlsanity.com/paper/2608.11681/) (2026)

## Abstract (arXiv)

Generalized zero-shot semantic segmentation of 3D point clouds aims to classify each point into both seen and unseen classes. A significant challenge with these models is their tendency to make biased predictions, often favoring the classes encountered during training. This problem is more pronounced in 3D applications, where the scale of the training data is typically smaller than in image-based tasks. To address this problem, we propose a novel method called E3DPC-GZSL, which reduces overconfident predictions towards seen classes without relying on separate classifiers for seen and unseen data. E3DPC-GZSL tackles the overconfidence problem by integrating an evidence-based uncertainty estimator into a classifier. This estimator is then used to adjust prediction probabilities using a dynamic calibrated stacking factor that accounts for pointwise prediction uncertainty. In addition, E3DPC-GZSL introduces a novel training strategy that improves uncertainty estimation by refining the semantic space. This is achieved by merging learnable parameters with text-derived features, thereby improving model optimization for unseen data. Extensive experiments demonstrate that the proposed approach achieves state-of-the-art performance on generalized zero-shot semantic segmentation datasets, including ScanNet v2 and S3DIS.