Learning Placeholders for Open-Set Recognition

TL;DR

Proser introduces a novel approach for open-set recognition by learning data and classifier placeholders, enabling models to better identify and reject unknown classes while maintaining accuracy on known classes.

Contribution

The paper proposes Proser, a method that learns placeholders for data and classifiers to improve open-set recognition capabilities.

Findings

Proser effectively detects unknown classes in various datasets.

It transforms closed-set training into open-set training using data placeholders.

The method maintains high accuracy on known classes while rejecting unknowns.

Abstract

Traditional classifiers are deployed under closed-set setting, with both training and test classes belong to the same set. However, real-world applications probably face the input of unknown categories, and the model will recognize them as known ones. Under such circumstances, open-set recognition is proposed to maintain classification performance on known classes and reject unknowns. The closed-set models make overconfident predictions over familiar known class instances, so that calibration and thresholding across categories become essential issues when extending to an open-set environment. To this end, we proposed to learn PlaceholdeRs for Open-SEt Recognition (Proser), which prepares for the unknown classes by allocating placeholders for both data and classifier. In detail, learning data placeholders tries to anticipate open-set class data, thus transforms closed-set training into open-set training. Besides, to learn the invariant information between target and non-target classes, we reserve classifier placeholders as the class-specific boundary between known and unknown. The proposed Proser efficiently generates novel class by manifold mixup, and adaptively sets the value of reserved open-set classifier during training. Experiments on various datasets validate the effectiveness of our proposed method.