arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.00522cs.LGcs.ITmath.IT
收藏

从信息论视角分析变分自编码器中的多模态融合

Analyzing Multimodal Integration in the Variational Autoencoder from an Information-Theoretic Perspective

Hamburg University of Technology(汉堡工业大学);Humboldt-Universität zu Berlin(柏林洪堡大学);Federal Institute for Materials Research and Testing(联邦材料研究与测试研究所);Santa Fe Institute(圣塔菲研究所);Leipzig University(莱比锡大学)

Carlotta Langer, Yasmin Kim Georgie, Ilja Porohovoj, Verena Vanessa Hafner, Nihat Ay

AI总结:

本研究从信息论视角分析多模态变分自编码器的模态融合机制,提出单模态误差与精度损失两类度量指标,探究不同加权调度下潜损失对多模态融合能力的影响,为机器人系统的多模态学习提供分析依据。

摘要:

人类感知本质上是多模态的。例如,我们会将视觉、本体感觉和触觉信息整合为单一体验。因此,多模态学习对于构建旨在与真实世界进行稳健交互的机器人系统至关重要。已被提出用于多模态融合的一种潜在模型是多模态变分自编码器。变分自编码器(VAE)由两个网络组成:一个编码器,负责将数据映射到随机潜空间;一个解码器,负责从该潜空间的元素中重建数据。多模态VAE会在两个时间点将来自不同模态的输入在潜空间中融合,因此可作为机器人智能体的控制器。在本研究中,我们采用该架构,并引入信息论度量指标,以分析不同模态的融合对输入数据重建的重要程度。为此,我们计算了两类不同的度量指标:第一类称为单模态误差,用于评估单个模态的信息对该模态自身或所有模态重建的重要性。第二类名为精度损失,用于衡量仅缺失一种模态的信息时,对该模态重建或整个向量重建的影响。VAE通过证据下界进行训练,该下界可表示为两项之和,即重建损失和潜损失。潜损失的影响可通过一个额外变量加权,该变量的引入是为了应对后验坍缩问题。在本研究中,我们采用四种不同的加权调度训练网络,并就其多模态融合能力展开分析。

英文摘要:

Human perception is inherently multimodal. We integrate, for instance, visual, proprioceptive and tactile information into one experience. Hence, multimodal learning is of importance for building robotic systems that aim at robustly interacting with the real world. One potential model that has been proposed for multimodal integration is the multimodal variational autoencoder. A variational autoencoder (VAE) consists of two networks, an encoder that maps the data to a stochastic latent space and a decoder that reconstruct this data from an element of this latent space. The multimodal VAE integrates inputs from different modalities at two points in time in the latent space and can thereby be used as a controller for a robotic agent. Here we use this architecture and introduce information-theoretic measures in order to analyze how important the integration of the different modalities are for the reconstruction of the input data. Therefore we calculate two different types of measures, the first type is called single modality error and assesses how important the information from a single modality is for the reconstruction of this modality or all modalities. Secondly, the measures named loss of precision calculate the impact that missing information from only one modality has on the reconstruction of this modality or the whole vector. The VAE is trained via the evidence lower bound, which can be written as a sum of two different terms, namely the reconstruction and the latent loss. The impact of the latent loss can be weighted via an additional variable, which has been introduced to combat posterior collapse. Here we train networks with four different weighting schedules and analyze them with respect to their capabilities for multimodal integration.

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。

↑