# A Case for Rejection in Low Resource ML Deployment

arXiv: https://arxiv.org/abs/2208.06359 · HTML: https://mlsanity.com/paper/2208.06359/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 12 Aug 2022.

## Builds on (most cited first, 10 of 10)

- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Likelihood Ratios for Out-of-Distribution Detection](https://mlsanity.com/paper/1906.02845/) (2019)
- [SelectiveNet: A Deep Neural Network with an Integrated Reject Option](https://mlsanity.com/paper/1901.09192/) (2019)
- [Machine Learning with a Reject Option: A survey](https://mlsanity.com/paper/2107.11277/) (2021)
- [Automatic Moth Detection from Trap Images for Pest Management](https://mlsanity.com/paper/1602.07383/) (2016)
- [ATRO: Adversarial Training with a Rejection Option](https://mlsanity.com/paper/2010.12905/) (2020)
- [Support Vector Machine (SVM) Recognition Approach adapted to Individual and Touching Moths Counting in Trap Images](https://mlsanity.com/paper/1809.06663/) (2018)

## Built on by (most cited first, 2 of 2)

- [BOLLWM: A real-world dataset for bollworm pest monitoring from cotton fields in India](https://mlsanity.com/paper/2304.00763/) (2023)
- [Maintaining User Trust Through Multistage Uncertainty Aware Inference](https://mlsanity.com/paper/2402.00015/) (2023)

## Abstract (arXiv)

Building reliable AI decision support systems requires a robust set of data on which to train models; both with respect to quantity and diversity. Obtaining such datasets can be difficult in resource limited settings, or for applications in early stages of deployment. Sample rejection is one way to work around this challenge, however much of the existing work in this area is ill-suited for such scenarios. This paper substantiates that position and proposes a simple solution as a proof of concept baseline.