Addressing Missing and Noisy Modalities in One Solution: Unified Modality-Quality Framework for Low-quality Multimodal Data

TL;DR

A unified modality-quality (UMQ) framework to enhance low-quality representations for multimodal affective computing and proposes a quality-aware mixture-of-experts module with particular routing mechanism to enable multiple modality-quality problems to be addressed more specifically.

Abstract

Multimodal data encountered in real-world scenarios are typically of low quality, with noisy modalities and missing modalities being typical forms that severely hinder model performance and robustness. However, prior works often handle noisy and missing modalities separately. In contrast, we jointly address missing and noisy modalities to enhance model robustness in low-quality data scenarios. We regard both noisy and missing modalities as a unified low-quality modality problem, and propose a unified modality-quality (UMQ) framework to enhance low-quality representations for multimodal affective computing. Firstly, we train a quality estimator with explicit supervised signals via a rank-guided training strategy that compares the relative quality of different representations by adding a ranking constraint, avoiding training noise caused by inaccurate absolute quality labels. Then, a quality enhancer for each modality is constructed, which uses the sample-specific information provided by other modalities and the modality-specific information provided by the defined modality baseline representation to enhance the quality of unimodal representations. Finally, we propose a quality-aware mixture-of-experts module with particular routing mechanism to enable multiple modality-quality problems to be addressed more specifically. UMQ consistently outperforms state-of-the-art baselines on multiple datasets under the settings of complete, missing, and noisy modalities.

Figures (8)

• Figure 1: An example of missing and noisy modalities.
• Figure 2: Diagram of UMQ and the training objectives of the proposed components.
• Figure 3: Visualization of the original and reconstructed language features. 'UMQ' and 'W/O MSI' denote the reconstructed features obtained by our method and obtained without modality-specific information, respectively.
• Figure 4: Analysis on estimated quality and selected experts. The modalities enclosed by the red bounding box are replaced with Gaussian noise.
• Figure 5: The MAE of UMQ with respect to the change of loss weights on CMU-MOSEI.