Modality Invariant Multimodal Learning to Handle Missing Modalities: A Single-Branch Approach
- URL: http://arxiv.org/abs/2408.07445v1
- Date: Wed, 14 Aug 2024 10:32:16 GMT
- Title: Modality Invariant Multimodal Learning to Handle Missing Modalities: A Single-Branch Approach
- Authors: Muhammad Saad Saeed, Shah Nawaz, Muhammad Zaigham Zaheer, Muhammad Haris Khan, Karthik Nandakumar, Muhammad Haroon Yousaf, Hassan Sajjad, Tom De Schepper, Markus Schedl,
- Abstract summary: We propose a modality invariant multimodal learning method, which is less susceptible to the impact of missing modalities.
It consists of a single-branch network sharing weights across multiple modalities to learn inter-modality representations to maximize performance.
Our proposed method achieves superior performance when all modalities are present as well as in the case of missing modalities during training or testing compared to the existing state-of-the-art methods.
- Score: 29.428067329993173
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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 deteriorated performance if one or more modalities are missing. In this work, we propose a modality invariant multimodal learning method, which is less susceptible to the impact of missing modalities. It consists of a single-branch network sharing weights across multiple modalities to learn inter-modality representations to maximize performance as well as robustness to missing modalities. Extensive experiments are performed on four challenging datasets including textual-visual (UPMC Food-101, Hateful Memes, Ferramenta) and audio-visual modalities (VoxCeleb1). Our proposed method achieves superior performance when all modalities are present as well as in the case of missing modalities during training or testing compared to the existing state-of-the-art methods.
Related papers
- U2A: Unified Unimodal Adaptation for Robust and Efficient Multimodal Learning [10.909746391230206]
We present Unified Unimodal Adaptation (U2A), which jointly fine-tunes unimodal encoders using low-rank adaptation (LoRA) for various multimodal tasks.
Our method significantly reduces the number of learnable parameters and eliminates the need for complex training strategies.
Mask Tokens (MT) generate missing modality features from available modalities using a single token per modality.
arXiv Detail & Related papers (2025-01-29T18:15:49Z) - Asymmetric Reinforcing against Multi-modal Representation Bias [59.685072206359855]
We propose an Asymmetric Reinforcing method against Multimodal representation bias (ARM)
Our ARM dynamically reinforces the weak modalities while maintaining the ability to represent dominant modalities through conditional mutual information.
We have significantly improved the performance of multimodal learning, making notable progress in mitigating imbalanced multimodal learning.
arXiv Detail & Related papers (2025-01-02T13:00:06Z) - Chameleon: Images Are What You Need For Multimodal Learning Robust To Missing Modalities [17.723207830420996]
Multimodal learning methods often exhibit deteriorated performances if one or more modalities are missing.
We propose a robust textual-visual multimodal learning method, Chameleon, that completely deviates from the conventional multi-branch design.
Experiments are performed on four popular datasets including Hateful Memes, UPMC Food-101, MM-IMDb, and Ferramenta.
arXiv Detail & Related papers (2024-07-23T07:29:57Z) - Missing Modality Prediction for Unpaired Multimodal Learning via Joint Embedding of Unimodal Models [6.610033827647869]
In real-world scenarios, consistently acquiring complete multimodal data presents significant challenges.
This often leads to the issue of missing modalities, where data for certain modalities are absent.
We propose a novel framework integrating parameter-efficient fine-tuning of unimodal pretrained models with a self-supervised joint-embedding learning method.
arXiv Detail & Related papers (2024-07-17T14:44:25Z) - Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition [52.522244807811894]
We propose a novel multimodal Transformer framework using prompt learning to address the issue of missing modalities.
Our method introduces three types of prompts: generative prompts, missing-signal prompts, and missing-type prompts.
Through prompt learning, we achieve a substantial reduction in the number of trainable parameters.
arXiv Detail & Related papers (2024-07-07T13:55:56Z) - Exploring Missing Modality in Multimodal Egocentric Datasets [89.76463983679058]
We introduce a novel concept -Missing Modality Token (MMT)-to maintain performance even when modalities are absent.
Our method mitigates the performance loss, reducing it from its original $sim 30%$ drop to only $sim 10%$ when half of the test set is modal-incomplete.
arXiv Detail & Related papers (2024-01-21T11:55:42Z) - Multimodal Representation Learning by Alternating Unimodal Adaptation [73.15829571740866]
We propose MLA (Multimodal Learning with Alternating Unimodal Adaptation) to overcome challenges where some modalities appear more dominant than others during multimodal learning.
MLA reframes the conventional joint multimodal learning process by transforming it into an alternating unimodal learning process.
It captures cross-modal interactions through a shared head, which undergoes continuous optimization across different modalities.
Experiments are conducted on five diverse datasets, encompassing scenarios with complete modalities and scenarios with missing modalities.
arXiv Detail & Related papers (2023-11-17T18:57:40Z) - Unified Multi-modal Unsupervised Representation Learning for
Skeleton-based Action Understanding [62.70450216120704]
Unsupervised pre-training has shown great success in skeleton-based action understanding.
We propose a Unified Multimodal Unsupervised Representation Learning framework, called UmURL.
UmURL exploits an efficient early-fusion strategy to jointly encode the multi-modal features in a single-stream manner.
arXiv Detail & Related papers (2023-11-06T13:56:57Z) - Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation [16.17270247327955]
We propose a simple and parameter-efficient adaptation procedure for pretrained multimodal networks.
We demonstrate that such adaptation can partially bridge performance drop due to missing modalities.
Our proposed method demonstrates versatility across various tasks and datasets, and outperforms existing methods for robust multimodal learning with missing modalities.
arXiv Detail & Related papers (2023-10-06T03:04:21Z) - Exploiting modality-invariant feature for robust multimodal emotion
recognition with missing modalities [76.08541852988536]
We propose to use invariant features for a missing modality imagination network (IF-MMIN)
We show that the proposed model outperforms all baselines and invariantly improves the overall emotion recognition performance under uncertain missing-modality conditions.
arXiv Detail & Related papers (2022-10-27T12:16:25Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.