We consider the problem of complementary fashion prediction. Existing approaches focus on learning an embedding space where fashion items from different categories that are visually compatible are closer to each other. However, creating such labeled outfits is intensive and also not feasible to generate all possible outfit combinations, especially with large fashion catalogs. In this work, we propose a semi-supervised learning approach where we leverage large unlabeled fashion corpus to create pseudo-positive and pseudo-negative outfits on the fly during training. For each labeled outfit in a training batch, we obtain a pseudo-outfit by matching each item in the labeled outfit with unlabeled items. Additionally, we introduce consistency regularization to ensure that representation of the original images and their transformations are consistent to implicitly incorporate colour and other important attributes through self-supervision. We conduct extensive experiments on Polyvore, Polyvore-D and our newly created large-scale Fashion Outfits datasets, and show that our approach with only a fraction of labeled examples performs on-par with completely supervised methods.
翻译:我们考虑的是补充时装预测问题。 现有方法侧重于学习嵌入空间, 让不同类别、视觉相容的时装物品相互接近。 但是, 创建这种贴标签的服装是密集的, 也不可能生成所有可能的服装组合, 特别是大型时装目录。 在这项工作中, 我们提出一个半监督的学习方法, 利用大型无标签的时装材料在飞行中制造假阳性和伪阴性服装。 对于每组培训中贴标签的服装, 我们得到一个假装配, 将每件贴标签的服装与无标签的物品配对。 此外, 我们引入一致性规范, 以确保原始图像及其变换的表达方式一致, 以隐含的方式将颜色和其他重要属性包含在自我监督的图像中。 我们在聚变型、 聚变型- D 和我们新创建的大型时装数据集上进行广泛的实验, 并展示我们只用部分标签的例子在完全监督的方法上进行。