Open Set Learning
47 papers with code • 0 benchmarks • 3 datasets
Traditional supervised learning aims to train a classifier in the closed-set world, where training and test samples share the same label space. Open set learning (OSL) is a more challenging and realistic setting, where there exist test samples from the classes that are unseen during training. Open set recognition (OSR) is the sub-task of detecting test images which do not come from the training.
These leaderboards are used to track progress in Open Set Learning
Modern deep neural networks are well known to be brittle in the face of unknown data instances and recognition of the latter remains a challenge.
Opposite-Direction Feature Attack (ODFA) effectively exploits feature-level adversarial gradients and takes advantage of feature distance in the representation space.
In this survey, we first present a generic framework called generalized OOD detection, which encompasses the five aforementioned problems, i. e., AD, ND, OSR, OOD detection, and OD.
The third oriental language recognition (OLR) challenge AP18-OLR is introduced in this paper, including the data profile, the tasks and the evaluation principles.
Existing open-set classifiers rely on deep networks trained in a supervised manner on known classes in the training set; this causes specialization of learned representations to known classes and makes it hard to distinguish unknowns from knowns.
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.