Open set face recognition using transduction

By Fayin Li, Harry Wechsler. 2005

178 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

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

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

iCaRL: Incremental Classifier and Representation Learning (2016, background): “…standard classification loss, which encourages improvements of the feature representation that allow classifying the newly observed classes well, it also contains the distillation loss, which ensures that the discriminative information learned previously is not lost during the new learning step.”
Towards Open World Recognition (2014, background): “is incomplete knowledge of the world at training time, and unknown classes can be submitted to an algorithm during testing [20, 34].”
A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning (2020, background): “This can work surprisingly well in models with thorough understanding of the decision boundary and its neighborhood, such as the Transduction Confidence Machine-k Nearest Neighbors (TCM-kNN) (Li and Wechsler, 2005).”
Learning Placeholders for Open-Set Recognition (2021, background): “However, this closed-world assumption comes to an end when the test set includes unseen categories [16, 2, 42, 35].”
Recent Advances in Open Set Recognition: A Survey (2018, neutral): “In a study on evaluation methods for face recognition, Phillips et al. [44] proposed a typical framework for open set identity recognition, while Li and Wechsler [45] again viewed open set face recognition from an evaluation perspective and proposed Open Set TCM-kNN (Transduction Conﬁdence Machine-k”
Learning with Augmented Class by Exploiting Unlabeled Data (2014, methodology): “It has been applied in face recognition (Li and Wechsler 2005), speaker recognition (Reynolds 2002), etc.”
Learning and the Unknown: Surveying Steps toward Open World Recognition (2019, background): “, a K-nearest neighbor with a threshold on an appropriate measure (Li and Wechsler 2005) or threshold on one or more one-class classifiers (Tax and Duin 2008; Liu et al.”
Open Set Domain Adaptation (2017, background): “These open sets started getting attention in face recognition tasks, where some test exemplars did not appear in the training database and had to be rejected [28].”
Cyberspace Security Using Adversarial Learning and Conformal Prediction (2015, background): “” PSEI can be addressed using meta-reasoning and transduction [26] to recognize attack patterns that are difficult to defend against, and thus to gate and process them accordingly (see Sect.”
Vision based hand gesture recognition for human computer interaction: a survey (2012, methodology): “Mgestyk developed in 2009 (Li and Wechsler 2005; Mgestyk 2009) employs software for hand gesture processing and 3D camera to interact with computer for operating games and applications.”