# Locating and Mitigating Gradient Conflicts in Point Cloud Domain Adaptation via Saliency Map Skewness

arXiv: https://arxiv.org/abs/2504.15796 · HTML: https://mlsanity.com/paper/2504.15796/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 22 Apr 2025.

## Builds on (most cited first, 19 of 19)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [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)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Conflict-Averse Gradient Descent for Multi-task Learning](https://mlsanity.com/paper/2110.14048/) (2021)
- [Distribution Alignment: A Unified Framework for Long-tail Visual Recognition](https://mlsanity.com/paper/2103.16370/) (2021)
- [PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation](https://mlsanity.com/paper/1911.02744/) (2019)
- [PointCloud Saliency Maps](https://mlsanity.com/paper/1812.01687/) (2018)
- [Self-Supervised Learning for Domain Adaptation on Point-Clouds](https://mlsanity.com/paper/2003.12641/) (2020)
- [MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks](https://mlsanity.com/paper/2203.06801/) (2022)
- [Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds](https://mlsanity.com/paper/2108.09169/) (2021)
- [Domain Adaptation on Point Clouds via Geometry-Aware Implicits](https://mlsanity.com/paper/2112.09343/) (2021)
- [Joint Supervised and Self-Supervised Learning for 3D Real-World Challenges](https://mlsanity.com/paper/2004.07392/) (2020)
- [Salvage Reusable Samples from Noisy Data for Robust Learning](https://mlsanity.com/paper/2008.02427/) (2020)
- [Self-Distillation for Unsupervised 3D Domain Adaptation](https://mlsanity.com/paper/2210.08226/) (2022)
- [Interpreting Hidden Semantics in the Intermediate Layers of 3D Point Cloud Classification Neural Network](https://mlsanity.com/paper/2303.06652/) (2023)

## Abstract (arXiv)

Object classification models utilizing point cloud data are fundamental for 3D media understanding, yet they often struggle with unseen or out-of-distribution (OOD) scenarios. Existing point cloud unsupervised domain adaptation (UDA) methods typically employ a multi-task learning (MTL) framework that combines primary classification tasks with auxiliary self-supervision tasks to bridge the gap between cross-domain feature distributions. However, our further experiments demonstrate that not all gradients from self-supervision tasks are beneficial and some may negatively impact the classification performance. In this paper, we propose a novel solution, termed Saliency Map-based Data Sampling Block (SM-DSB), to mitigate these gradient conflicts. Specifically, our method designs a new scoring mechanism based on the skewness of 3D saliency maps to estimate gradient conflicts without requiring target labels. Leveraging this, we develop a sample selection strategy that dynamically filters out samples whose self-supervision gradients are not beneficial for the classification. Our approach is scalable, introducing modest computational overhead, and can be integrated into all the point cloud UDA MTL frameworks. Extensive evaluations demonstrate that our method outperforms state-of-the-art approaches. In addition, we provide a new perspective on understanding the UDA problem through back-propagation analysis.