Beyond Domain Adaptation: Unseen Domain Encapsulation via Universal Non-volume Preserving Models
This addresses the challenge of deploying deep learning models in new, unseen domains without the ability to update or adapt them, which is crucial for real-world applications like recognition tasks.
The paper tackles the problem of domain generalization for deep learning models when encountering unseen domains where adaptation is impossible, proposing a Universal Non-volume Preserving approach that integrates with ConvNet frameworks. Results show improved performance on digit recognition, face recognition, and pedestrian detection across multiple benchmark datasets compared to state-of-the-art methods.
Recognition across domains has recently become an active topic in the research community. However, it has been largely overlooked in the problem of recognition in new unseen domains. Under this condition, the delivered deep network models are unable to be updated, adapted or fine-tuned. Therefore, recent deep learning techniques, such as: domain adaptation, feature transferring, and fine-tuning, cannot be applied. This paper presents a novel Universal Non-volume Preserving approach to the problem of domain generalization in the context of deep learning. The proposed method can be easily incorporated with any other ConvNet framework within an end-to-end deep network design to improve the performance. On digit recognition, we benchmark on four popular digit recognition databases, i.e. MNIST, USPS, SVHN and MNIST-M. The proposed method is also experimented on face recognition on Extended Yale-B, CMU-PIE and CMU-MPIE databases and compared against other the state-of-the-art methods. In the problem of pedestrian detection, we empirically observe that the proposed method learns models that improve performance across a priori unknown data distributions.