Self-supervised Visual Attribute Learning for Fashion Compatibility
arxiv(2021)
摘要
Many self-supervised learning (SSL) methods have been successful in learning semantically meaningful visual representations by solving pretext tasks. However, state-of-the-art SSL methods focus on object recognition or detection tasks, which aim to learn object shapes, but ignore visual attributes such as color and texture via color distortion augmentation. However, learning these visual attributes could be more important than learning object shapes for other vision tasks, such as fashion compatibility. To address this deficiency, we propose Self-supervised Tasks for Outfit Compatibility (STOC) without any supervision. Specifically, STOC aims to learn colors and textures of fashion items and embed similar items nearby. STOC outperforms state-of-the-art SSL by 9.5% and a supervised Siamese Network by 3% on a fill-in-the-blank outfit completion task on our unsupervised benchmark.
更多查看译文
关键词
object shapes,downstream tasks,critical information,SSL framework,texture-aware features,self-supervised tasks,color histograms,shapeless local patches,fashion compatibility,Polyvore Outfits,Deep-fashion,prior SSL methods,supervised approaches,transfer learning,self-supervised visual attribute learning,self-supervised learning methods,semantically meaningful visual representations,pretext tasks,object recognition
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络