Fashion style classification is a challenging task because of the large visual variation within the same style and the existence of visually similar styles. Styles are expressed not only by the global appearance, but also by the attributes of individual items and their combinations. In this study, we propose an item region-based fashion style classification network (IRSN) to effectively classify fashion styles by analyzing item-specific features and their combinations in addition to global features. IRSN extracts features of each item region using item region pooling (IRP), analyzes them separately, and combines them using gated feature fusion (GFF). In addition, we improve the feature extractor by applying a dual-backbone architecture that combines a domain-specific feature extractor and a general feature extractor pre-trained with a large-scale image-text dataset. In experiments, applying IRSN to six widely-used backbones, including EfficientNet, ConvNeXt, and Swin Transformer, improved style classification accuracy by an average of 6.9% and a maximum of 14.5% on the FashionStyle14 dataset and by an average of 7.6% and a maximum of 15.1% on the ShowniqV3 dataset. Visualization analysis also supports that the IRSN models are better than the baseline models at capturing differences between similar style classes.

翻译：时尚风格分类是一项具有挑战性的任务，原因在于同一风格内部存在较大的视觉差异，以及存在视觉上相似的风格。风格的表达不仅依赖于整体外观，还依赖于单个服装单品的属性及其组合方式。在本研究中，我们提出了一种基于服装单品区域的时尚风格分类网络（IRSN），旨在通过分析全局特征、单品特定特征及其组合，来有效分类时尚风格。IRSN利用单品区域池化（IRP）提取每个单品区域的特征，分别对其进行分析，并通过门控特征融合（GFF）进行组合。此外，我们通过应用一种双主干架构改进了特征提取器，该架构结合了特定领域特征提取器和在大规模图文数据集上预训练的通用特征提取器。在实验中，将IRSN应用于包括EfficientNet、ConvNeXt和Swin Transformer在内的六个广泛使用的主干网络时，在FashionStyle14数据集上，风格分类准确率平均提升了6.9%，最高提升了14.5%；在ShowniqV3数据集上，平均提升了7.6%，最高提升了15.1%。可视化分析也支持IRSN模型在捕捉相似风格类别间差异方面优于基线模型。