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 2104.08489cs.LGcs.CV
收藏

具有最优传输的半监督多模多实例多标记深度网络

Semi-Supervised Multi-Modal Multi-Instance Multi-Label Deep Network with Optimal Transport

Nanjing University(南京大学);Tencent WXG(腾讯微信事业群)

Yang Yang, Zhao-Yang Fu, De-Chuan Zhan, Zhi-Bin Liu, Yuan Jiang

摘要:

复杂对象通常具有多个标签,并且可以由多个模态表示来表示,例如,复杂的文章包含文本和图像信息以及多个注释。以前的方法假设同质多模态数据是一致的,而在实际应用中,原始数据是无序的,例如,文章由可变数量的不一致文本和图像实例构成。因此,多模态多实例多标签(M3)学习提供了一个框架来处理这样的任务,并表现出优异的性能。然而,M3学习面临着两个主要挑战:1)如何有效地利用标签相关性; 2)如何利用多模态学习来处理未标记的实例。为了解决这些问题,我们首先提出了一种新的多模式多实例多标签深度网络(M3 DN),它在端到端的多模式深度网络中考虑M3学习,并利用不同模式袋级预测之间的一致性原则。基于M3 DN,我们学习潜在的地面标签度量与最佳传输。此外,我们引入了外部的未标记的多模态多实例数据,并提出了M3 DNS,它考虑了实例级的自动编码器的单一模态和修改袋级的最佳传输,以加强模态之间的一致性。因此,M3 DNS可以更好地预测标签并同时利用标签相关性。在基准数据集和真实世界WKG Game-Hub数据集上的实验验证了所提方法的有效性。

英文摘要:

Complex objects are usually with multiple labels, and can be represented by multiple modal representations, e.g., the complex articles contain text and image information as well as multiple annotations. Previous methods assume that the homogeneous multi-modal data are consistent, while in real applications, the raw data are disordered, e.g., the article constitutes with variable number of inconsistent text and image instances. Therefore, Multi-modal Multi-instance Multi-label (M3) learning provides a framework for handling such task and has exhibited excellent performance. However, M3 learning is facing two main challenges: 1) how to effectively utilize label correlation; 2) how to take advantage of multi-modal learning to process unlabeled instances. To solve these problems, we first propose a novel Multi-modal Multi-instance Multi-label Deep Network (M3DN), which considers M3 learning in an end-to-end multi-modal deep network and utilizes consistency principle among different modal bag-level predictions. Based on the M3DN, we learn the latent ground label metric with the optimal transport. Moreover, we introduce the extrinsic unlabeled multi-modal multi-instance data, and propose the M3DNS, which considers the instance-level auto-encoder for single modality and modified bag-level optimal transport to strengthen the consistency among modalities. Thereby M3DNS can better predict label and exploit label correlation simultaneously. Experiments on benchmark datasets and real world WKG Game-Hub dataset validate the effectiveness of the proposed methods.

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。

↑