A unifying review of deep and shallow anomaly detection

L Ruff, JR Kauffmann, RA Vandermeulen… - Proceedings of the …, 2021‏ - ieeexplore.ieee.org
Deep learning approaches to anomaly detection (AD) have recently improved the state of
the art in detection performance on complex data sets, such as large collections of images or …

Recent advances in open set recognition: A survey

C Geng, S Huang, S Chen - IEEE transactions on pattern …, 2020‏ - ieeexplore.ieee.org
In real-world recognition/classification tasks, limited by various objective factors, it is usually
difficult to collect training samples to exhaust all classes when training a recognizer or …

To trust or not to trust a classifier

H Jiang, B Kim, M Guan… - Advances in neural …, 2018‏ - proceedings.neurips.cc
Knowing when a classifier's prediction can be trusted is useful in many applications and
critical for safely using AI. While the bulk of the effort in machine learning research has been …

Two-stage learning to defer with multiple experts

A Mao, C Mohri, M Mohri… - Advances in neural …, 2023‏ - proceedings.neurips.cc
We study a two-stage scenario for learning to defer with multiple experts, which is crucial in
practice for many applications. In this scenario, a predictor is derived in a first stage by …

Machine learning with a reject option: A survey

K Hendrickx, L Perini, D Van der Plas, W Meert… - Machine Learning, 2024‏ - Springer
Abstract Machine learning models always make a prediction, even when it is likely to be
inaccurate. This behavior should be avoided in many decision support applications, where …

Learning with rejection

C Cortes, G DeSalvo, M Mohri - … Conference, ALT 2016, Bari, Italy, October …, 2016‏ - Springer
We introduce a novel framework for classification with a rejection option that consists of
simultaneously learning two functions: a classifier along with a rejection function. We …

Multi-class open set recognition using probability of inclusion

LP Jain, WJ Scheirer, TE Boult - … September 6-12, 2014, Proceedings, Part …, 2014‏ - Springer
The perceived success of recent visual recognition approaches has largely been derived
from their performance on classification tasks, where all possible classes are known at …

Towards robust pattern recognition: A review

XY Zhang, CL Liu, CY Suen - Proceedings of the IEEE, 2020‏ - ieeexplore.ieee.org
The accuracies for many pattern recognition tasks have increased rapidly year by year,
achieving or even outperforming human performance. From the perspective of accuracy …

Training uncertainty-aware classifiers with conformalized deep learning

BS Einbinder, Y Romano, M Sesia… - Advances in neural …, 2022‏ - proceedings.neurips.cc
Deep neural networks are powerful tools to detect hidden patterns in data and leverage
them to make predictions, but they are not designed to understand uncertainty and estimate …

Theoretically grounded loss functions and algorithms for score-based multi-class abstention

A Mao, M Mohri, Y Zhong - International Conference on …, 2024‏ - proceedings.mlr.press
Learning with abstention is a key scenario where the learner can abstain from making a
prediction at some cost. In this paper, we analyze the score-based formulation of learning …