# Example Perplexity

arXiv: https://arxiv.org/abs/2203.08813 · HTML: https://mlsanity.com/paper/2203.08813/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 10 references that are in the map.
- First posted on arXiv 16 Mar 2022.

## Builds on (most cited first, 6 of 6)

- [Are we done with ImageNet?](https://mlsanity.com/paper/2006.07159/) (2020)
- [From ImageNet to Image Classification: Contextualizing Progress on Benchmarks](https://mlsanity.com/paper/2005.11295/) (2020)
- [Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade](https://mlsanity.com/paper/1704.01344/) (2017)
- [How hard can it be? Estimating the difficulty of visual search in an image](https://mlsanity.com/paper/1705.08280/) (2017)
- [Difficulty-aware Glaucoma Classification with Multi-Rater Consensus Modeling](https://mlsanity.com/paper/2007.14848/) (2020)
- [Efficient Image Dataset Classification Difficulty Estimation for Predicting Deep-Learning Accuracy](https://mlsanity.com/paper/1803.09588/) (2018)

## Abstract (arXiv)

Some examples are easier for humans to classify than others. The same should be true for deep neural networks (DNNs). We use the term example perplexity to refer to the level of difficulty of classifying an example. In this paper, we propose a method to measure the perplexity of an example and investigate what factors contribute to high example perplexity. The related codes and resources are available at https://github.com/vaynexie/Example-Perplexity.