Work entitled "The iMaterialist Fashion Attribute Dataset" won the Best Paper Award at the ICCV '19 Second Workshop on Computer Vision for Fashion, Art, and Design (CVFAD) in Seoul, Korea. Authors include recent Cornell CS Ph.D., Yin Cui along with Sheng Guo, Weilin Huang, Xiao Zhang, Prasanna Srikhanta, Yuan Li, Matthew Scott, Adam Hartwig, and CS Professor and Associate Dean of Cornell Tech, Serge Belongie.
Large-scale image databases such as ImageNet have significantly advanced image classification and other visual recognition tasks. However much of these datasets are constructed only for single-label and coarse object-level classification. For real-world applications, multiple labels and fine-grained categories are often needed, yet very few such datasets exist publicly, especially those of large-scale and high quality. In this work, we contribute to the community a new dataset called iMaterialist Fashion Attribute (iFashion-Attribute) to address this problem in the fashion domain. The dataset is constructed from over one million fashion images with a label space that includes 8 groups of 228 fine-grained attributes in total. Each image is annotated by experts with multiple, high-quality fashion attributes. The result is the first known million-scale multi-label and fine-grained image dataset. We conduct extensive experiments and provide baseline results with modern deep Convolutional Neural Networks (CNNs). Additionally, we demonstrate models pre-trained on iFashion-Attribute achieve superior transfer learning performance on fashion related tasks compared with pre-training from ImageNet or other fashion datasets. Data is available at this location.