# Training Decision Trees as Replacement for Convolution Layers

arXiv: https://arxiv.org/abs/1905.10073 · HTML: https://mlsanity.com/paper/1905.10073/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2019.

## Built on by (most cited first, 10 of 10)

- [TEyeD: Over 20 million real-world eye images with Pupil, Eyelid, and Iris 2D and 3D Segmentations, 2D and 3D Landmarks, 3D Eyeball, Gaze Vector, and Eye Movement Types](https://mlsanity.com/paper/2102.02115/) (2021)
- [The Gaze and Mouse Signal as additional Source for User Fingerprints in Browser Applications](https://mlsanity.com/paper/2101.03793/) (2021)
- [A Multimodal Eye Movement Dataset and a Multimodal Eye Movement Segmentation Analysis](https://mlsanity.com/paper/2101.04318/) (2021)
- [1000 Pupil Segmentations in a Second using Haar Like Features and Statistical Learning](https://mlsanity.com/paper/2102.01921/) (2021)
- [Maximum and Leaky Maximum Propagation](https://mlsanity.com/paper/2105.10277/) (2021)
- [Tensor Normalization and Full Distribution Training](https://mlsanity.com/paper/2109.02345/) (2021)
- [GroupGazer: A Tool to Compute the Gaze per Participant in Groups with integrated Calibration to Map the Gaze Online to a Screen or Beamer Projection](https://mlsanity.com/paper/2201.07692/) (2022)
- [PEACH: Pretrained-embedding Explanation Across Contextual and Hierarchical Structure](https://mlsanity.com/paper/2404.13645/) (2024)
- [Technical Report: Combining knowledge from Transfer Learning during training and Wide Resnets](https://mlsanity.com/paper/2206.09697/) (2022)
- [GazeTrack: High-Precision Eye Tracking Based on Regularization and Spatial Computing](https://mlsanity.com/paper/2511.22607/) (2025)

## Abstract (arXiv)

We present an alternative layer to convolution layers in convolutional neural networks (CNNs). Our approach reduces the complexity of convolutions by replacing it with binary decisions. Those binary decisions are used as indexes to conditional distributions where each weight represents a leaf in a decision tree. This means that only the indices to the weights need to be determined once, thus reducing the complexity of convolutions by the depth of the output tensor. Index computation is performed by simple binary decisions that require fewer cycles compared to conventionally used multiplications. In addition, we show how convolutions can be replaced by binary decisions. These binary decisions form indices in the conditional distributions and we show how they are used to replace 2D weight matrices as well as 3D weight tensors. These new layers can be trained like convolution layers in CNNs based on the backpropagation algorithm, for which we provide a formalization. Our results on multiple publicly available data sets show that our approach performs similar to conventional neuronal networks. Beyond the formalized reduction of complexity and the improved qualitative performance, we show the runtime improvement empirically compared to convolution layers.