Multi-class Open Set Recognition Using Probability of Inclusion

By Lalit P. Jain, Walter J. Scheirer, Terrance E. Boult. 2014

390 citations recorded by the source corpus.

How researchers see this paper

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

In Artificial Intelligence

Citations in the corpus

Towards Open World Object Detection (2021, background): “Follow up works [23, 59] extended the open set framework to multi-class classiﬁer setting with probabilistic models to account for the fading away classiﬁer conﬁdences in case of unknown classes.”
DOC: Deep Open Classification of Text Documents (2017, neutral): “In 2014).”
Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly (2017, background): “[60] argues that although ImageNet classification challenge performance has reached beyond human performance, we do not observe similar behavior of the methods that compete at the detection challenge which involves rejecting unknown objects while detecting the position and label of a known object.”
Zero-Shot Learning — The Good, the Bad and the Ugly (2017, background): “[19] argues that although ImageNet classification challenge performance has reached beyond human performance, we do not observe similar behavior of the methods that compete at the detection challenge which involves rejecting unknown objects while detecting the position and label of a known object.”
Zero-Shot Object Detection (2018, neutral): “This proposed approach is also related to open-vocabulary learning where we are not restricted by a ﬁxed set of classes [20,57], and to latent-variable based classiﬁcation models e.g. [49].”
Learning Cumulatively to Become More Knowledgeable (2016, methodology): “Following that in [11, 18], we conduct open world crossvalidation style evaluation, holding out some classes in training and mixing them back during testing, and varying the number of training and test classes.”
An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild (2016, background): “Finally, open set recognition [35,36,37] considers testing on both types of classes, but treating the unseen ones as a single outlier class.”
Recent Advances in Open Set Recognition: A Survey (2018, methodology): “Under different openness O∗, Table 3 reports the comparisons among these methods, where 1-vs-Set [21], W-SVM (WOSVM7) [22], PI -SVM [23], SROSR [61], OSNN [73], EVM [74] from Traditional ML-based category and CD-OSR [63] from the Non-Instance Generation-based category.”
Open Set Learning with Counterfactual Images (2018, methodology): “Some approaches involve learning a feature space through classification of training data, then detecting outliers in that feature space at test time [4] [5].”
Local Novelty Detection in Multi-class Recognition Problems (2015, background): “This corresponds to analyzing the “openness” of a classiﬁcation problem in open set recognition [19, 32].”
Learning to Transfer Examples for Partial Domain Adaptation (2019, background): “Domain Adaptation On par with domain adaptation, research has been dedicated to open set recognition, with the goal to reject outliers while correctly recognizing inliers during testing. Open Set SVM [18] trains a probabilistic SVM and rejects unknown samples by a threshold. Open Set Neural Network ”
Open Set Domain Adaptation by Backpropagation (2018, background): “The ﬁrst baseline is an open set SVM (OSVM) [24].”
Generative OpenMax for Multi-Class Open Set Classification (2017, methodology): “replication of the experiment performed in [11], where 6 classes are hold out in training and the rest 4 classes are used to varying “openness”.”
C2AE: Class Conditioned Auto-Encoder for Open-Set Recognition (2019, methodology): “There have been many methods that explore these questions in the context of traditional methods such as Support Vector Machines [44], [45], [18], Nearest Neighbors [21], [6] and Sparse Representation [50].”
WildFish: A Large Benchmark for Fish Recognition in the Wild (2018, background): “To address the open-set problem, a number of machine learning approaches have been proposed by 1-vs-Set Machine [35], W-SVM [33], P I -SVM [23], Nearest Non-Outlier (NNO) [3], etc. Recently, the remarkable successes of convolutional neural networks (CNNs) [9, 18, 20, 24, 37, 38, 45] have promoted…”
A Survey of Zero-Shot Learning (2019, methodology): “In open set recognition methods [64, 132], when learning the classifier with the training data, the fact of unseen classes existing is taken in consideration.”
Discriminative Partial Domain Adversarial Network (2020, background): “Moreover, there are also some related DA problem setup like [12,23] focus on universial and openset DA problems.”