DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation
This addresses domain adaptation for visual recognition tasks, providing an incremental improvement over existing methods.
The paper tackled the problem of domain shifts in computer vision by proposing DeepJDOT, a method that aligns joint deep representations and labels between source and target domains using optimal transport, resulting in favorable performance compared to state-of-the-art deep domain adaptation methods.
In computer vision, one is often confronted with problems of domain shifts, which occur when one applies a classifier trained on a source dataset to target data sharing similar characteristics (e.g. same classes), but also different latent data structures (e.g. different acquisition conditions). In such a situation, the model will perform poorly on the new data, since the classifier is specialized to recognize visual cues specific to the source domain. In this work we explore a solution, named DeepJDOT, to tackle this problem: through a measure of discrepancy on joint deep representations/labels based on optimal transport, we not only learn new data representations aligned between the source and target domain, but also simultaneously preserve the discriminative information used by the classifier. We applied DeepJDOT to a series of visual recognition tasks, where it compares favorably against state-of-the-art deep domain adaptation methods.