相关论文: Modality Competition: What Makes Joint Training of…

Consider end-to-end training of a multi-modal vs. a single-modal network on a task with multiple input modalities: the multi-modal network receives more information, so it should match or outperform its single-modal counterpart. In our…

The world provides us with data of multiple modalities. Intuitively, models fusing data from different modalities outperform their uni-modal counterparts, since more information is aggregated. Recently, joining the success of deep learning,…

While the field of multi-modal learning keeps growing fast, the deficiency of the standard joint training paradigm has become clear through recent studies. They attribute the sub-optimal performance of the jointly trained model to the…

Ensembles of machine learning models have been well established as a powerful method of improving performance over a single model. Traditionally, ensembling algorithms train their base learners independently or sequentially with the goal of…

Training a multimodal network is challenging and it requires complex architectures to achieve reasonable performance. We show that one reason for this phenomena is the difference between the convergence rate of various modalities. We…

Multimodal learning assumes all modality combinations of interest are available during training to learn cross-modal correspondences. In this paper, we challenge this modality-complete assumption for multimodal learning and instead strive…

Multimodal learning often encounters the under-optimized problem and may have worse performance than unimodal learning. Existing methods attribute this problem to the imbalanced learning between modalities and rebalance them through…

We abstract the features (i.e. learned representations) of multi-modal data into 1) uni-modal features, which can be learned from uni-modal training, and 2) paired features, which can only be learned from cross-modal interactions.…

To overcome the imbalanced multimodal learning problem, where models prefer the training of specific modalities, existing methods propose to control the training of uni-modal encoders from different perspectives, taking the inter-modal…

Multimodal learning often outperforms its unimodal counterparts by exploiting unimodal contributions and cross-modal interactions. However, focusing only on integrating multimodal features into a unified comprehensive representation…

Multimodal deep learning, especially vision-language models, have gained significant traction in recent years, greatly improving performance on many downstream tasks, including content moderation and violence detection. However, standard…

Many vision-related tasks benefit from reasoning over multiple modalities to leverage complementary views of data in an attempt to learn robust embedding spaces. Most deep learning-based methods rely on a late fusion technique whereby…

Multimodal networks have demonstrated remarkable performance improvements over their unimodal counterparts. Existing multimodal networks are designed in a multi-branch fashion that, due to the reliance on fusion strategies, exhibit…

Learning multi-modal representations is an essential step towards real-world robotic applications, and various multi-modal fusion models have been developed for this purpose. However, we observe that existing models, whose objectives are…

We aim to develop a fundamental understanding of modality collapse, a recently observed empirical phenomenon wherein models trained for multimodal fusion tend to rely only on a subset of the modalities, ignoring the rest. We show that…

Multimodal learning integrates information from different modalities to enhance model performance, yet it often suffers from modality imbalance, where dominant modalities overshadow weaker ones during joint optimization. This paper reveals…

Combining complementary information from multiple modalities is intuitively appealing for improving the performance of learning-based approaches. However, it is challenging to fully leverage different modalities due to practical challenges…

Using multiple input streams simultaneously to train multimodal neural networks is intuitively advantageous but practically challenging. A key challenge is unimodal bias, where a network overly relies on one modality and ignores others…

Multimodal Re-Identification (ReID) is a popular retrieval task that aims to re-identify objects across diverse data streams, prompting many researchers to integrate multiple modalities into a unified representation. While such fusion…

During multimodal model training and testing, certain data modalities may be absent due to sensor limitations, cost constraints, privacy concerns, or data loss, negatively affecting performance. Multimodal learning techniques designed to…