Classification with reject option

By Radu Herbei, Marten H. Wegkamp. 2006

281 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/2737f255ee233d8b8b4113bfbe0fa370908b8d78

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Statistics and Probability

Citations in the corpus

Learning with Rejection (2016, background): “Herbei and Wegkamp [18] considered classification with a rejection option that incurs a cost and provided bounds for these ternary functions.”
Practical Ensemble Classification Error Bounds for Different Operating Points (2013, background): “As another example, consider an analyst at a national security agency who must find instances of terrorist chatter in petabytes of internet traffic to then be investigated.”
Hybrid Models with Deep and Invertible Features (2019, background): “This idea is also known as selective clas-siﬁcation or classiﬁcation with a reject option (Hellman, 1970; Cordella et al., 1995; Fumera & Roli, 2002; Herbei & Wegkamp, 2006; Geifman & El-Yaniv, 2017).”
Least Ambiguous Set-Valued Classifiers With Bounded Error Levels (2016, methodology): “For example, Herbei & Wegkamp (2006) assigns a constant loss d ∈ (0 , 1 / 2) for the output “reject”, while del Coz et al. (2009) deﬁnes the loss function as a weighted combination of precision and recall in an information retrieval framework.”
On the Foundations of Noise-free Selective Classification (2010, background): “This popular cost model was refined to accommodate differentiation between the cost of false positive and false negative as well as different costs for rejection of positive and negative samples (Herbei and Wegkamp, 2006; Pietraszek, 2005; Tortorella, 2001; Santos-Pereira and Pires, 2005).”
Classification with a Reject Option using a Hinge Loss (2008, methodology): “For plug-in rules, Herbei and Wegkamp (2006) showed an analogous result for classification with a reject option , where the corresponding condition concerns the probability that η(X) is close to the critical values of d and 1 − d.”
Do Deep Generative Models Know What They Don't Know? (2018, background): “…example for which we require accurate densities, and others include information regularization (Szummer & Jaakkola, 2003), open set recognition (Herbei & Wegkamp, 2006), uncertainty estimation, detecting covariate shift, active learning, model-based reinforcement learning, and transfer…”
To Trust Or Not To Trust A Classifier (2018, background): “The problem of classification with a reject option or learning with abstention [16, 17, 18, 19, 20, 21, 22] is a highly related framework where the classifier is allowed to abstain from making a prediction at a certain cost.”
Recent Advances in Open Set Recognition: A Survey (2018, background): “It should be noted that there have been already a variety of works in the literature regarding classification with reject option [35], [36], [37], [38], [39], [40], [41], [42], [43], [44], [45].”
Prototype-based Neural Network Layers: Incorporating Vector Quantization (2018, methodology): “This geometrical perspective makes the method attractive for outlier detection and related reject strategies [44, 45, 46, 47, 48, 49, 50].”
Mitigating Concept Drift via Rejection (2018, background): “Pioneered by Chow [4], who derived optimal reject rules if true class probabilities are known, a number of extensions of learning with reject options have been proposed for batch learning scenarios, such as plugin rules for class probabilities [5], efficient surrogate losses [6, 7], or optimal combi”
Agnostic Selective Classification (2011, unknown): “They empirically compared their results with two other selective classifiers: the one proposed by Bartlett and Wegkamp [20] and the traditional rejection based on distance from decision boundary.”
Aleatoric and Epistemic Uncertainty in Machine Learning: A Tutorial Introduction (2019, background): “Another example appears in the literature on binary or multi-class classification with reject option (Herbei and Wegkamp, 2006; Linusson et al., 2018; Ramaswamy et al., 2015).”