Adaptive SVM+: Learning with Privileged Information for Domain Adaptation
This work addresses domain adaptation in computer vision by leveraging auxiliary data, offering incremental improvements for tasks like visual recognition.
The paper tackles the challenge of using privileged information from different distributions in domain adaptation for visual recognition, proposing Adaptive SVM+ which integrates learning using privileged information and domain adaptation, achieving state-of-the-art results on Animals with Attributes and INTERACT datasets.
Incorporating additional knowledge in the learning process can be beneficial for several computer vision and machine learning tasks. Whether privileged information originates from a source domain that is adapted to a target domain, or as additional features available at training time only, using such privileged (i.e., auxiliary) information is of high importance as it improves the recognition performance and generalization. However, both primary and privileged information are rarely derived from the same distribution, which poses an additional challenge to the recognition task. To address these challenges, we present a novel learning paradigm that leverages privileged information in a domain adaptation setup to perform visual recognition tasks. The proposed framework, named Adaptive SVM+, combines the advantages of both the learning using privileged information (LUPI) paradigm and the domain adaptation framework, which are naturally embedded in the objective function of a regular SVM. We demonstrate the effectiveness of our approach on the publicly available Animals with Attributes and INTERACT datasets and report state-of-the-art results in both of them.