Universal Domain Adaptation in Ordinal Regression
This work addresses domain adaptation challenges in ordinal regression tasks like age estimation, which is incremental as it adapts existing UDA techniques to a specific setting.
The paper tackled the problem of universal domain adaptation in ordinal regression, where labels have a natural order, by proposing a method that combines an auxiliary order learning task with adversarial domain discrimination. The result showed that their model outperformed baseline methods on three face age estimation datasets.
We address the problem of universal domain adaptation (UDA) in ordinal regression (OR), which attempts to solve classification problems in which labels are not independent, but follow a natural order. We show that the UDA techniques developed for classification and based on the clustering assumption, under-perform in OR settings. We propose a method that complements the OR classifier with an auxiliary task of order learning, which plays the double role of discriminating between common and private instances, and expanding class labels to the private target images via ranking. Combined with adversarial domain discrimination, our model is able to address the closed set, partial and open set configurations. We evaluate our method on three face age estimation datasets, and show that it outperforms the baseline methods.