Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration
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_ | 1866916461716439040 |
|---|---|
| author | Pan, Kaihang Fan, Zhaoyu Li, Juncheng Yu, Qifan Fei, Hao Tang, Siliang Hong, Richang Zhang, Hanwang Sun, Qianru |
| author_facet | Pan, Kaihang Fan, Zhaoyu Li, Juncheng Yu, Qifan Fei, Hao Tang, Siliang Hong, Richang Zhang, Hanwang Sun, Qianru |
| contents | The swift advancement in Multimodal LLMs (MLLMs) also presents significant challenges for effective knowledge editing. Current methods, including intrinsic knowledge editing and external knowledge resorting, each possess strengths and weaknesses, struggling to balance the desired properties of reliability, generality, and locality when applied to MLLMs. In this paper, we propose UniKE, a novel multimodal editing method that establishes a unified perspective and paradigm for intrinsic knowledge editing and external knowledge resorting. Both types of knowledge are conceptualized as vectorized key-value memories, with the corresponding editing processes resembling the assimilation and accommodation phases of human cognition, conducted at the same semantic levels. Within such a unified framework, we further promote knowledge collaboration by disentangling the knowledge representations into the semantic and truthfulness spaces. Extensive experiments validate the effectiveness of our method, which ensures that the post-edit MLLM simultaneously maintains excellent reliability, generality, and locality. The code for UniKE is available at \url{https://github.com/beepkh/UniKE}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_19872 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration Pan, Kaihang Fan, Zhaoyu Li, Juncheng Yu, Qifan Fei, Hao Tang, Siliang Hong, Richang Zhang, Hanwang Sun, Qianru Computer Vision and Pattern Recognition The swift advancement in Multimodal LLMs (MLLMs) also presents significant challenges for effective knowledge editing. Current methods, including intrinsic knowledge editing and external knowledge resorting, each possess strengths and weaknesses, struggling to balance the desired properties of reliability, generality, and locality when applied to MLLMs. In this paper, we propose UniKE, a novel multimodal editing method that establishes a unified perspective and paradigm for intrinsic knowledge editing and external knowledge resorting. Both types of knowledge are conceptualized as vectorized key-value memories, with the corresponding editing processes resembling the assimilation and accommodation phases of human cognition, conducted at the same semantic levels. Within such a unified framework, we further promote knowledge collaboration by disentangling the knowledge representations into the semantic and truthfulness spaces. Extensive experiments validate the effectiveness of our method, which ensures that the post-edit MLLM simultaneously maintains excellent reliability, generality, and locality. The code for UniKE is available at \url{https://github.com/beepkh/UniKE}. |
| title | Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.19872 |