A Case for Rejection in Low Resource ML Deployment
Not on the map. Why?
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.
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
10 of 20 references.
References · 10
- 2015SSD: Single Shot MultiBox Detectorcited by 3,130
- 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
- 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
- 2017Selective Classification for Deep Neural Networkscited by 852
- 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
- 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 350
- 2021Machine Learning with a Reject Option: A surveycited by 109
- 2016Automatic Moth Detection from Trap Images for Pest Managementcited by 10
- 2020ATRO: Adversarial Training with a Rejection Optioncited by 8
- 2018Support Vector Machine (SVM) Recognition Approach adapted to Individual and Touching Moths Counting in Trap Imagescited by 2
Built on by
Citing papers per year: 2023: 2.
2 papers.