# Evolutionary Neural Architecture Search for 3D Point Cloud Analysis

arXiv: https://arxiv.org/abs/2408.05556 · HTML: https://mlsanity.com/paper/2408.05556/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 32 references that are in the map.
- First posted on arXiv 10 Aug 2024.

## Builds on (most cited first, 10 of 10)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [Genetic CNN](https://mlsanity.com/paper/1703.01513/) (2017)
- [Knowledge Fusion By Evolving Weights of Language Models](https://mlsanity.com/paper/2406.12208/) (2024)
- [CADE: Cosine Annealing Differential Evolution for Spiking Neural Network](https://mlsanity.com/paper/2406.02349/) (2024)
- [A Tunnel Gaussian Process Model for Learning Interpretable Flight's Landing Parameters](https://mlsanity.com/paper/2011.09335/) (2020)
- [PIDS: Joint Point Interaction-Dimension Search for 3D Point Cloud](https://mlsanity.com/paper/2211.15759/) (2022)

## Built on by (most cited first, 1 of 1)

- [Parameter Competition Balancing for Model Merging](https://mlsanity.com/paper/2410.02396/) (2024)

## Abstract (arXiv)

Neural architecture search (NAS) automates neural network design by using optimization algorithms to navigate architecture spaces, reducing the burden of manual architecture design. While NAS has achieved success, applying it to emerging domains, such as analyzing unstructured 3D point clouds, remains underexplored due to the data lying in non-Euclidean spaces, unlike images. This paper presents Success-History-based Self-adaptive Differential Evolution with a Joint Point Interaction Dimension Search (SHSADE-PIDS), an evolutionary NAS framework that encodes discrete deep neural network architectures to continuous spaces and performs searches in the continuous spaces for efficient point cloud neural architectures. Comprehensive experiments on challenging 3D segmentation and classification benchmarks demonstrate SHSADE-PIDS's capabilities. It discovered highly efficient architectures with higher accuracy, significantly advancing prior NAS techniques. For segmentation on SemanticKITTI, SHSADE-PIDS attained 64.51% mean IoU using only 0.55M parameters and 4.5GMACs, reducing overhead by over 22-26X versus other top methods. For ModelNet40 classification, it achieved 93.4% accuracy with just 1.31M parameters, surpassing larger models. SHSADE-PIDS provided valuable insights into bridging evolutionary algorithms with neural architecture optimization, particularly for emerging frontiers like point cloud learning.