# Exploring the Sharpened Cosine Similarity

arXiv: https://arxiv.org/abs/2307.13855 · HTML: https://mlsanity.com/paper/2307.13855/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 14 references that are in the map.
- First posted on arXiv 25 Jul 2023.

## Builds on (most cited first, 5 of 5)

- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [A Step Toward Quantifying Independently Reproducible Machine Learning Research](https://mlsanity.com/paper/1909.06674/) (2019)
- [Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networks](https://mlsanity.com/paper/1702.05870/) (2017)
- [Research Reproducibility as a Survival Analysis](https://mlsanity.com/paper/2012.09932/) (2020)
- [A Siren Song of Open Source Reproducibility](https://mlsanity.com/paper/2204.04372/) (2022)

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

- [Neighborhood Feature Pooling for Remote Sensing Image Classification](https://mlsanity.com/paper/2510.25077/) (2025)

## Abstract (arXiv)

Convolutional layers have long served as the primary workhorse for image classification. Recently, an alternative to convolution was proposed using the Sharpened Cosine Similarity (SCS), which in theory may serve as a better feature detector. While multiple sources report promising results, there has not been to date a full-scale empirical analysis of neural network performance using these new layers. In our work, we explore SCS's parameter behavior and potential as a drop-in replacement for convolutions in multiple CNN architectures benchmarked on CIFAR-10. We find that while SCS may not yield significant increases in accuracy, it may learn more interpretable representations. We also find that, in some circumstances, SCS may confer a slight increase in adversarial robustness.