Collective decision for open set recognition

Understand

In open set recognition (OSR), almost all existing methods are designed specially for recognizing individual instances, even these instances are collectively coming in batch.

• Recognizers in decision either reject or categorize them to some known class using empirically-set threshold.
• Thus the decision threshold plays a key role.
• However, the selection for it usually depends on the knowledge of known classes, inevitably incurring risks due to lacking available information from unknown classes.