A cascade of deep classifiers detects new classes at test time and increments the model with a one-class leaf per new class, reporting better average performance than three baselines on RF device and Twitter datasets.
Bayesian Nonexhaustive Learning for Online Discovery and Modeling of Emerging Classes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We present a framework for online inference in the presence of a nonexhaustively defined set of classes that incorporates supervised classification with class discovery and modeling. A Dirichlet process prior (DPP) model defined over class distributions ensures that both known and unknown class distributions originate according to a common base distribution. In an attempt to automatically discover potentially interesting class formations, the prior model is coupled with a suitably chosen data model, and sequential Monte Carlo sampling is used to perform online inference. Our research is driven by a biodetection application, where a new class of pathogen may suddenly appear, and the rapid increase in the number of samples originating from this class indicates the onset of an outbreak.
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi-stage Deep Classifier Cascades for Open World Recognition
A cascade of deep classifiers detects new classes at test time and increments the model with a one-class leaf per new class, reporting better average performance than three baselines on RF device and Twitter datasets.