Image retrieval under generalized test scenarios has gained significant momentum in literature, and the recently proposed protocol of Universal Cross-domain Retrieval is a pioneer in this direction. A common practice in any such generalized classification or retrieval algorithm is to exploit samples from many domains during training to learn a domain-invariant representation of data. Such criterion is often restrictive, and thus in this work, for the first time, we explore the generalized retrieval problem in a data-efficient manner. Specifically, we aim to generalize any pre-trained cross-domain retrieval network towards any unknown query domain/category, by means of adapting the model on the test data leveraging self-supervised learning techniques. Toward that goal, we explored different self-supervised loss functions~(for example, RotNet, JigSaw, Barlow Twins, etc.) and analyze their effectiveness for the same. Extensive experiments demonstrate the proposed approach is simple, easy to implement, and effective in handling data-efficient UCDR.
翻译:在广义测试情况下的图像检索在文献中获得了极大的发展,最近提出的Universal Cross-domain Retrieval协议是这方面的先驱。在任何这样的广义分类或检索算法中,通常的做法是在训练时利用许多域的样本来学习数据的域不变表示,但这个标准往往是过于严苛的。因此,在本工作中,我们首次以数据有效的方式探讨了广义检索问题。具体地,我们旨在通过利用自监督学习技术来调整模型来适应测试数据,从而将任何预先训练的跨域检索网络推广到任何未知的查询域/类别。为此,我们探索了不同的自监督损失函数(例如,RotNet、JigSaw、Barlow Twins等),并分析了它们的有效性。大量的实验证明了所提出的方法简单易行,对于处理数据有效的Universal Cross-domain Retrieval十分有效。