Opening Deep Neural Networks with Generative Models
This addresses the hazard of recognition failures in real-world image classification where unknown classes may appear, offering a simple solution for domain-specific applications.
The authors tackled the problem of open set recognition in deep visual learning by proposing GeMOS, a plug-and-play module that attaches to pretrained neural networks, which either outperforms or matches state-of-the-art methods in object recognition tasks.
Image classification methods are usually trained to perform predictions taking into account a predefined group of known classes. Real-world problems, however, may not allow for a full knowledge of the input and label spaces, making failures in recognition a hazard to deep visual learning. Open set recognition methods are characterized by the ability to correctly identify inputs of known and unknown classes. In this context, we propose GeMOS: simple and plug-and-play open set recognition modules that can be attached to pretrained Deep Neural Networks for visual recognition. The GeMOS framework pairs pre-trained Convolutional Neural Networks with generative models for open set recognition to extract open set scores for each sample, allowing for failure recognition in object recognition tasks. We conduct a thorough evaluation of the proposed method in comparison with state-of-the-art open set algorithms, finding that GeMOS either outperforms or is statistically indistinguishable from more complex and costly models.