EPE-P: Evidence-based Parameter-efficient Prompting for Multimodal Learning with Missing Modalities
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929645364969472 |
|---|---|
| author | Chen, Zhe Lin, Xun Cui, Yawen Yu, Zitong |
| author_facet | Chen, Zhe Lin, Xun Cui, Yawen Yu, Zitong |
| contents | Missing modalities are a common challenge in real-world multimodal learning scenarios, occurring during both training and testing. Existing methods for managing missing modalities often require the design of separate prompts for each modality or missing case, leading to complex designs and a substantial increase in the number of parameters to be learned. As the number of modalities grows, these methods become increasingly inefficient due to parameter redundancy. To address these issues, we propose Evidence-based Parameter-Efficient Prompting (EPE-P), a novel and parameter-efficient method for pretrained multimodal networks. Our approach introduces a streamlined design that integrates prompting information across different modalities, reducing complexity and mitigating redundant parameters. Furthermore, we propose an Evidence-based Loss function to better handle the uncertainty associated with missing modalities, improving the model's decision-making. Our experiments demonstrate that EPE-P outperforms existing prompting-based methods in terms of both effectiveness and efficiency. The code is released at https://github.com/Boris-Jobs/EPE-P_MLLMs-Robustness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_17677 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EPE-P: Evidence-based Parameter-efficient Prompting for Multimodal Learning with Missing Modalities Chen, Zhe Lin, Xun Cui, Yawen Yu, Zitong Computer Vision and Pattern Recognition Missing modalities are a common challenge in real-world multimodal learning scenarios, occurring during both training and testing. Existing methods for managing missing modalities often require the design of separate prompts for each modality or missing case, leading to complex designs and a substantial increase in the number of parameters to be learned. As the number of modalities grows, these methods become increasingly inefficient due to parameter redundancy. To address these issues, we propose Evidence-based Parameter-Efficient Prompting (EPE-P), a novel and parameter-efficient method for pretrained multimodal networks. Our approach introduces a streamlined design that integrates prompting information across different modalities, reducing complexity and mitigating redundant parameters. Furthermore, we propose an Evidence-based Loss function to better handle the uncertainty associated with missing modalities, improving the model's decision-making. Our experiments demonstrate that EPE-P outperforms existing prompting-based methods in terms of both effectiveness and efficiency. The code is released at https://github.com/Boris-Jobs/EPE-P_MLLMs-Robustness. |
| title | EPE-P: Evidence-based Parameter-efficient Prompting for Multimodal Learning with Missing Modalities |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.17677 |