Learning to Generalize One Sample at a Time with Self-Supervision
This work addresses the problem of reducing costly data annotation for domain adaptation and generalization in visual recognition, though it appears incremental by building on existing self-supervised and auxiliary learning methods.
The paper tackles the challenge of achieving robust visual recognition across domains with minimal data annotation by proposing a self-supervised learning approach for domain generalization and adaptation, using an auxiliary learning framework and learning from target data during testing; results on three scenarios confirm its value.
Although deep networks have significantly increased the performance of visual recognition methods, it is still challenging to achieve the robustness across visual domains that is necessary for real-world applications. To tackle this issue, research on domain adaptation and generalization has flourished over the last decade. An important aspect to consider when assessing the work done in the literature so far is the amount of data annotation necessary for training each approach, both at the source and target level. In this paper we argue that the data annotation overload should be minimal, as it is costly. Hence, we propose to use self-supervised learning to achieve domain generalization and adaptation. We consider learning regularities from non annotated data as an auxiliary task, and cast the problem within an Auxiliary Learning principled framework. Moreover, we suggest to further exploit the ability to learn about visual domains from non annotated images by learning from target data while testing, as data are presented to the algorithm one sample at a time. Results on three different scenarios confirm the value of our approach.