39 citations · 154 across the 26 of their papers we have counts for
9 papers · 1 filter
Open Set Domain Adaptation by Extreme Value Theory
Yiming Xu, Diego Klabjan
Common domain adaptation techniques assume that the source domain and the target domain share an identical label space, which is problematic since when target samples are unlabeled…
Concept Drift and Covariate Shift Detection Ensemble with Lagged Labels
Yiming Xu, Diego Klabjan
In model serving, having one fixed model during the entire often life-long inference process is usually detrimental to model performance, as data distribution evolves over time, re…
Inverse Classification with Limited Budget and Maximum Number of Perturbed Samples
Jaehoon Koo, Diego Klabjan, Jean Utke
Most recent machine learning research focuses on developing new classifiers for the sake of improving classification accuracy. With many well-performing state-of-the-art classifier…
Efficient Architecture Search for Continual Learning
Qiang Gao, Zhipeng Luo, Diego Klabjan
Continual learning with neural networks is an important learning framework in AI that aims to learn a sequence of tasks well. However, it is often confronted with three challenges:…
Open-Set Recognition with Gaussian Mixture Variational Autoencoders
Alexander Cao, Yuan Luo, Diego Klabjan
In inference, open-set classification is to either classify a sample into a known class from training or reject it as an unknown class. Existing deep open-set classifiers train exp…
Neural Network Retraining for Model Serving
Diego Klabjan, Xiaofeng Zhu
We propose incremental (re)training of a neural network model to cope with a continuous flow of new data in inference during model serving. As such, this is a life-long learning pr…