arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.15103cs.CVcs.IR
收藏

基于跨模态层次模型的细粒度草图图像检索

Cross-Modal Hierarchical Modelling for Fine-Grained Sketch Based Image Retrieval

University of Surrey(萨里大学)

Aneeshan Sain, Ayan Kumar Bhunia, Yongxin Yang, Tao Xiang, Yi-Zhe Song

摘要:

草图作为图像搜索查询是捕获细粒度视觉细节的文本的理想替代。先前在基于细粒度草图的图像检索(FG-SBIR)上的成功已经证明了处理草图而不是照片的独特特征的重要性,例如,时间与静态、笔划与像素以及抽象与像素完美。在本文中,我们研究了迄今为止被忽视的草图的另一个特点,即它们在细节层次方面是分层的-一个人通常会绘制各种程度的细节来描绘一个对象。这种层次结构通常在视觉上是不同的。在本文中,我们设计了一种新的网络,能够培养草图特定的层次结构,并利用它们来匹配草图与相应层次的照片。特别是,从草图和照片的特征是丰富使用跨模态的共同注意,再加上层次节点融合在每一个层次,形成一个更好的嵌入空间进行检索。常见的基准测试实验表明,我们的方法优于国家的最先进的显着保证金。

英文摘要:

Sketch as an image search query is an ideal alternative to text in capturing the fine-grained visual details. Prior successes on fine-grained sketch-based image retrieval (FG-SBIR) have demonstrated the importance of tackling the unique traits of sketches as opposed to photos, e.g., temporal vs. static, strokes vs. pixels, and abstract vs. pixel-perfect. In this paper, we study a further trait of sketches that has been overlooked to date, that is, they are hierarchical in terms of the levels of detail -- a person typically sketches up to various extents of detail to depict an object. This hierarchical structure is often visually distinct. In this paper, we design a novel network that is capable of cultivating sketch-specific hierarchies and exploiting them to match sketch with photo at corresponding hierarchical levels. In particular, features from a sketch and a photo are enriched using cross-modal co-attention, coupled with hierarchical node fusion at every level to form a better embedding space to conduct retrieval. Experiments on common benchmarks show our method to outperform state-of-the-arts by a significant margin.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑