Open-Set Representation Learning through Combinatorial Embedding
This work addresses the challenge of open-set recognition for visual tasks, enabling recognition of both known and novel classes, though it appears incremental as it builds on existing representation learning methods.
The paper tackles the problem of identifying novel concepts in datasets with limited labeled classes by proposing a combinatorial learning approach that clusters unseen classes using multiple supervised meta-classifiers and unsupervised pairwise relation learning, resulting in remarkable performance gains on public datasets for image retrieval and categorization.
Visual recognition tasks are often limited to dealing with a small subset of classes simply because the labels for the remaining classes are unavailable. We are interested in identifying novel concepts in a dataset through representation learning based on both labeled and unlabeled examples, and extending the horizon of recognition to both known and novel classes. To address this challenging task, we propose a combinatorial learning approach, which naturally clusters the examples in unseen classes using the compositional knowledge given by multiple supervised meta-classifiers on heterogeneous label spaces. The representations given by the combinatorial embedding are made more robust by unsupervised pairwise relation learning. The proposed algorithm discovers novel concepts via a joint optimization for enhancing the discrimitiveness of unseen classes as well as learning the representations of known classes generalizable to novel ones. Our extensive experiments demonstrate remarkable performance gains by the proposed approach on public datasets for image retrieval and image categorization with novel class discovery.