# Distance Based Image Classification: A solution to generative classification's conundrum?

arXiv: https://arxiv.org/abs/2210.01349 · HTML: https://mlsanity.com/paper/2210.01349/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 52 references that are in the map.
- First posted on arXiv 4 Oct 2022.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [Are we done with ImageNet?](https://mlsanity.com/paper/2006.07159/) (2020)
- [REMIND Your Neural Network to Prevent Catastrophic Forgetting](https://mlsanity.com/paper/1910.02509/) (2019)
- [Continual Unsupervised Representation Learning](https://mlsanity.com/paper/1910.14481/) (2019)
- [iTAML: An Incremental Task-Agnostic Meta-learning Approach](https://mlsanity.com/paper/2003.11652/) (2020)
- [Neural Architecture Transfer](https://mlsanity.com/paper/2005.05859/) (2020)
- [Class-Incremental Learning with Generative Classifiers](https://mlsanity.com/paper/2104.10093/) (2021)
- [Efficient L1-Norm Principal-Component Analysis via Bit Flipping](https://mlsanity.com/paper/1610.01959/) (2016)
- [Efficient Autotuning of Hyperparameters in Approximate Nearest Neighbor Search](https://mlsanity.com/paper/1812.07484/) (2018)
- [Dimensionality's Blessing: Clustering Images by Underlying Distribution](https://mlsanity.com/paper/1804.02624/) (2018)

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

- [Rethinking Unsupervised Outlier Detection via Multiple Thresholding](https://mlsanity.com/paper/2407.05382/) (2024)

## Abstract (arXiv)

Most classifiers rely on discriminative boundaries that separate instances of each class from everything else. We argue that discriminative boundaries are counter-intuitive as they define semantics by what-they-are-not; and should be replaced by generative classifiers which define semantics by what-they-are. Unfortunately, generative classifiers are significantly less accurate. This may be caused by the tendency of generative models to focus on easy to model semantic generative factors and ignore non-semantic factors that are important but difficult to model. We propose a new generative model in which semantic factors are accommodated by shell theory's hierarchical generative process and non-semantic factors by an instance specific noise term. We use the model to develop a classification scheme which suppresses the impact of noise while preserving semantic cues. The result is a surprisingly accurate generative classifier, that takes the form of a modified nearest-neighbor algorithm; we term it distance classification. Unlike discriminative classifiers, a distance classifier: defines semantics by what-they-are; is amenable to incremental updates; and scales well with the number of classes.