# Frequency-domain Learning for Volumetric-based 3D Data Perception

arXiv: https://arxiv.org/abs/2302.08595 · HTML: https://mlsanity.com/paper/2302.08595/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 16 references that are in the map.
- First posted on arXiv 16 Feb 2023.

## Builds on (most cited first, 9 of 9)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [Volumetric and Multi-View CNNs for Object Classification on 3D Data](https://mlsanity.com/paper/1604.03265/) (2016)
- [Learning in the Frequency Domain](https://mlsanity.com/paper/2002.12416/) (2020)
- [SEGCloud: Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/1710.07563/) (2017)
- [Generative and Discriminative Voxel Modeling with Convolutional Neural Networks](https://mlsanity.com/paper/1608.04236/) (2016)
- [Fast object detection in compressed JPEG Images](https://mlsanity.com/paper/1904.08408/) (2019)

## Abstract (arXiv)

Frequency-domain learning draws attention due to its superior tradeoff between inference accuracy and input data size. Frequency-domain learning in 2D computer vision tasks has shown that 2D convolutional neural networks (CNN) have a stationary spectral bias towards low-frequency channels so that high-frequency channels can be pruned with no or little accuracy degradation. However, frequency-domain learning has not been studied in the context of 3D CNNs with 3D volumetric data. In this paper, we study frequency-domain learning for volumetric-based 3D data perception to reveal the spectral bias and the accuracy-input-data-size tradeoff of 3D CNNs. Our study finds that 3D CNNs are sensitive to a limited number of critical frequency channels, especially low-frequency channels. Experiment results show that frequency-domain learning can significantly reduce the size of volumetric-based 3D inputs (based on spectral bias) while achieving comparable accuracy with conventional spatial-domain learning approaches. Specifically, frequency-domain learning is able to reduce the input data size by 98% in 3D shape classification while limiting the average accuracy drop within 2%, and by 98% in the 3D point cloud semantic segmentation with a 1.48% mean-class accuracy improvement while limiting the mean-class IoU loss within 1.55%. Moreover, by learning from higher-resolution 3D data (i.e., 2x of the original image in the spatial domain), frequency-domain learning improves the mean-class accuracy and mean-class IoU by 3.04% and 0.63%, respectively, while achieving an 87.5% input data size reduction in 3D point cloud semantic segmentation.