MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding
By: Zhicheng Zhang , Wuyou Xia , Chenxi Zhao and more
Potential Business Impact:
Helps computers understand pictures and words better.
Multimodal large language models (MLLMs) recently showed strong capacity in integrating data among multiple modalities, empowered by a generalizable attention architecture. Advanced methods predominantly focus on language-centric tuning while less exploring multimodal tokens mixed through attention, posing challenges in high-level tasks that require fine-grained cognition and emotion understanding. In this work, we identify the attention deficit disorder problem in multimodal learning, caused by inconsistent cross-modal attention and layer-by-layer decayed attention activation. To address this, we propose a novel attention mechanism, termed MOdular Duplex Attention (MODA), simultaneously conducting the inner-modal refinement and inter-modal interaction. MODA employs a correct-after-align strategy to effectively decouple modality alignment from cross-layer token mixing. In the alignment phase, tokens are mapped to duplex modality spaces based on the basis vectors, enabling the interaction between visual and language modality. Further, the correctness of attention scores is ensured through adaptive masked attention, which enhances the model's flexibility by allowing customizable masking patterns for different modalities. Extensive experiments on 21 benchmark datasets verify the effectiveness of MODA in perception, cognition, and emotion tasks. Source code and demo are available in https://zzcheng.top/MODA.
Similar Papers
MoDA: Modulation Adapter for Fine-Grained Visual Grounding in Instructional MLLMs
CV and Pattern Recognition
Helps computers understand pictures better with words.
ADMC: Attention-based Diffusion Model for Missing Modalities Feature Completion
Artificial Intelligence
Helps computers understand feelings even with missing clues.
Dynamic Multimodal Sentiment Analysis: Leveraging Cross-Modal Attention for Enabled Classification
Computation and Language
Helps computers understand feelings from voice, face, and words.