We define Open Long-Tailed Recognition (OLTR) as learning from such naturally distributed data and optimizing the classification accuracy over a balanced test set which include head, tail, and open classes.
We introduce a probabilistic approach to unify deep continual learning with open set recognition, based on variational Bayesian inference.
We present an analysis of predictive uncertainty based out-of-distribution detection for different approaches to estimate various models' epistemic uncertainty and contrast it with extreme value theory based open set recognition.
A typical challenge is that unknown samples may be fed into the system during the testing phase and traditional deep neural networks will wrongly recognize the unknown sample as one of the known classes.
We propose a generalized Sparse Representation- based Classification (SRC) algorithm for open set recognition where not all classes presented during testing are known during training.
Open set recognition problems exist in many domains.
The third oriental language recognition (OLR) challenge AP18-OLR is introduced in this paper, including the data profile, the tasks and the evaluation principles.
In the open-set scenario, however, a test sample can belong to none of the known classes and the classifier must properly reject it by classifying it as unknown.
Existing open set classifiers distinguish between known and unknown inputs by measuring distance in a network's logit space, assuming that known inputs cluster closer to the training data than unknown inputs.
Photo-identification (photo-id) of dolphin individuals is a commonly used technique in ecological sciences to monitor state and health of individuals, as well as to study the social structure and distribution of a population.