We propose a data-centric pipeline able to generate exogenous observation data for the New Fashion Product Performance Forecasting (NFPPF) problem, i.e., predicting the performance of a brand-new clothing probe with no available past observations. Our pipeline manufactures the missing past starting from a single, available image of the clothing probe. It starts by expanding textual tags associated with the image, querying related fashionable or unfashionable images uploaded on the web at a specific time in the past. A binary classifier is robustly trained on these web images by confident learning, to learn what was fashionable in the past and how much the probe image conforms to this notion of fashionability. This compliance produces the POtential Performance (POP) time series, indicating how performing the probe could have been if it were available earlier. POP proves to be highly predictive for the probe's future performance, ameliorating the sales forecasts of all state-of-the-art models on the recent VISUELLE fast-fashion dataset. We also show that POP reflects the ground-truth popularity of new styles (ensembles of clothing items) on the Fashion Forward benchmark, demonstrating that our webly-learned signal is a truthful expression of popularity, accessible by everyone and generalizable to any time of analysis. Forecasting code, data and the POP time series are available at: https://github.com/HumaticsLAB/POP-Mining-POtential-Performance
翻译:我们提议建立一个以数据为中心的管道,为新时装产品性能预测问题生成外源观测数据,即预测品牌新服装探测器的性能,而没有以往的观测。 我们的管道从服装探测器的单一、可用图像中制造缺失的过去。 它首先通过扩大与图像相关的文本标记,查询相关时装或不时装图像在过去某个特定时间上传到网上。 一个二进制分类器通过自信学习,在这些网络图像上强有力地训练了这些二进制分类器,以了解过去流行的东西,以及探测器图像与这种时装性概念的相符程度。 这种合规性生成了Pentiential 性能(POP)时间序列的时间序列序列,表明如果以前有的话,该探测器是如何运行的。 持久性有机污染物对探测器未来性能具有高度的预测力,改进了最近VISUELLE快速时装数据集中所有状态-艺术模型的销售预测。 我们还在 Vial-PI-S-Siral-comlifal 数据集中展示了我们可获取的每个时间-Siral-deal-malial-malial-deal-deal stabial stabial malistral romatistral latistral strismatistral matistral ex matistral ex