# Ternary and Binary Quantization for Improved Classification

arXiv: https://arxiv.org/abs/2203.16798 · HTML: https://mlsanity.com/paper/2203.16798/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 47 references that are in the map.
- First posted on arXiv 31 Mar 2022.

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

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [CNN Features off-the-shelf: an Astounding Baseline for Recognition](https://mlsanity.com/paper/1403.6382/) (2014)
- [Binary Neural Networks: A Survey](https://mlsanity.com/paper/2004.03333/) (2020)
- [Deep Convolutional Networks as shallow Gaussian Processes](https://mlsanity.com/paper/1808.05587/) (2018)
- [Deep Network Classification by Scattering and Homotopy Dictionary Learning](https://mlsanity.com/paper/1910.03561/) (2019)
- [Coding for Random Projections](https://mlsanity.com/paper/1308.2218/) (2013)
- [Ternary Hashing](https://mlsanity.com/paper/2103.09173/) (2021)
- [Deep Learning to Ternary Hash Codes by Continuation](https://mlsanity.com/paper/2107.07987/) (2021)

## Abstract (arXiv)

Dimension reduction and data quantization are two important methods for reducing data complexity. In the paper, we study the methodology of first reducing data dimension by random projection and then quantizing the projections to ternary or binary codes, which has been widely applied in classification. Usually, the quantization will seriously degrade the accuracy of classification due to high quantization errors. Interestingly, however, we observe that the quantization could provide comparable and often superior accuracy, as the data to be quantized are sparse features generated with common filters. Furthermore, this quantization property could be maintained in the random projections of sparse features, if both the features and random projection matrices are sufficiently sparse. By conducting extensive experiments, we validate and analyze this intriguing property.