Recent Ph.D., Yin Cui Wins Best Paper at ICCV '19 Workshop on CVFAD

　　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. 

　　在韩国首尔举行的第19届计算机视觉时尚、艺术和设计研讨会（CVFAD）上，题为“意象主义时尚属性数据集”的作品获得了最佳论文奖。作者包括康奈尔大学最近的CS博士、Yin Cui和Sheng Guo、Weilin Huang、Xiao Zhang、Prasanna Srikhanta、Yuan Li、Matthew Scott、Adam Hartwig，以及康奈尔大学的CS教授和副院长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. 

　　像ImageNet这样的大规模图像数据库具有显著的先进的图像分类和其他视觉识别任务。然而，这些数据集中的大部分都是为单标签和粗略的对象级分类而构建的。对于现实世界的应用，经常需要多个标签和细粒度的类别，但很少有这样的数据集公开存在，特别是那些大规模和高质量的。在这项工作中，我们为社区贡献了一个名为iMaterialist Fashion Attribute（iFashion Attribute）的新数据集来解决时尚领域中的这个问题。该数据集由超过一百万张时尚图片构成，标签空间包括8组共228个细粒度属性。每一张图片都由具有多种高质量时尚属性的专家进行注释。其结果是第一个已知的百万规模的多标签和细粒度图像数据集。我们进行了广泛的实验，并提供了现代深卷积神经网络（CNNs）的基线结果。此外，我们还展示了在iFashion属性上进行预训练的模型，与来自ImageNet或其他时尚数据集的预训练相比，在与时尚相关的任务上获得了更好的迁移学习性能。数据在此位置可用。

　　如需进一步了解，或有任何相关疑问，欢迎在线咨询留学专家。如果您对自己是否适合留学还有疑虑，欢迎参与前途出国免费评估，以便给您进行准确定位。