Beyond Domain Adaptation: Unseen Domain Encapsulation via Universal Non-volume Preserving Models

TL;DR

This paper introduces a universal non-volume preserving deep learning approach that enhances recognition performance across unseen domains without the need for model updates or fine-tuning.

Contribution

It proposes a novel universal non-volume preserving method for domain generalization applicable to any ConvNet framework, improving recognition in unseen domains.

Findings

Improved digit recognition across MNIST, USPS, SVHN, MNIST-M datasets.

Enhanced face recognition on Yale-B, CMU-PIE, CMU-MPIE datasets.

Better pedestrian detection performance on unknown data distributions.

Abstract

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.