Open-set classification is a problem of handling 'unknown' classes that are not contained in the training dataset, whereas traditional classifiers assume that only known classes appear in the test environment. 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. In contrast, we train networks for joint classification and reconstruction of input data. This enhances the learned representation so as to preserve information useful for separating unknowns from knowns, as well as to discriminate classes of knowns. Our novel Classification-Reconstruction learning for Open-Set Recognition (CROSR) utilizes latent representations for reconstruction and enables robust unknown detection without harming the known-class classification accuracy. Extensive experiments reveal that the proposed method outperforms existing deep open-set classifiers in multiple standard datasets and is robust to diverse outliers. The code is available in https://nae-lab.

Despite its implications for higher order functions of the brain, little is currently known about the molecular basis of left-right asymmetry of the brain. Here we report that synaptic distribution of N-methyl-D-aspartate (NMDA) receptor GluRepsilon2 (NR2B) subunits in the adult mouse hippocampus is asymmetrical between the left and right and between the apical and basal dendrites of single neurons. These asymmetrical allocations of epsilon2 subunits differentiate the properties of NMDA receptors and synaptic plasticity between the left and right hippocampus. These results provide a molecular basis for the structural and functional asymmetry of the mature brain.

No abstract