Mixture-of-Prompt-Experts for Multi-modal Semantic Understanding
- URL: http://arxiv.org/abs/2403.11311v2
- Date: Sun, 24 Mar 2024 06:21:27 GMT
- Title: Mixture-of-Prompt-Experts for Multi-modal Semantic Understanding
- Authors: Zichen Wu, Hsiu-Yuan Huang, Fanyi Qu, Yunfang Wu,
- Abstract summary: We propose Mixture-of-Prompt-Experts with Block-Aware Prompt Fusion (MoPE-BAF)
MoPE-BAF is a novel multi-modal soft prompt framework based on the unified vision-language model (VLM)
- Score: 7.329728566839757
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Deep multimodal semantic understanding that goes beyond the mere superficial content relation mining has received increasing attention in the realm of artificial intelligence. The challenges of collecting and annotating high-quality multi-modal data have underscored the significance of few-shot learning. In this paper, we focus on two critical tasks under this context: few-shot multi-modal sarcasm detection (MSD) and multi-modal sentiment analysis (MSA). To address them, we propose Mixture-of-Prompt-Experts with Block-Aware Prompt Fusion (MoPE-BAF), a novel multi-modal soft prompt framework based on the unified vision-language model (VLM). Specifically, we design three experts of soft prompts: a text prompt and an image prompt that extract modality-specific features to enrich the single-modal representation, and a unified prompt to assist multi-modal interaction. Additionally, we reorganize Transformer layers into several blocks and introduce cross-modal prompt attention between adjacent blocks, which smoothens the transition from single-modal representation to multi-modal fusion. On both MSD and MSA datasets in few-shot setting, our proposed model not only surpasses the 8.2B model InstructBLIP with merely 2% parameters (150M), but also significantly outperforms other widely-used prompt methods on VLMs or task-specific methods.
Related papers
- Multimodality Helps Few-Shot 3D Point Cloud Semantic Segmentation [61.91492500828508]
Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal support samples.
We introduce a cost-free multimodal FS-PCS setup, utilizing textual labels and the potentially available 2D image modality.
We propose a simple yet effective Test-time Adaptive Cross-modal Seg (TACC) technique to mitigate training bias.
arXiv Detail & Related papers (2024-10-29T19:28:41Z) - Multi-modal Semantic Understanding with Contrastive Cross-modal Feature
Alignment [11.897888221717245]
This paper proposes a novel CLIP-guided contrastive-learning-based architecture to perform multi-modal feature alignment.
Our model is simple to implement without using task-specific external knowledge, and thus can easily migrate to other multi-modal tasks.
arXiv Detail & Related papers (2024-03-11T01:07:36Z) - Browse and Concentrate: Comprehending Multimodal Content via prior-LLM Context Fusion [70.9767518332692]
Multimodal Large Language Models (MLLMs) that incorporate LLMs with pre-trained vision models have recently demonstrated impressive performance across diverse vision-language tasks.
However, they fall short to comprehend context involving multiple images.
We propose a two phase paradigm, browse-and-concentrate, to enable in-depth multimodal context fusion.
arXiv Detail & Related papers (2024-02-19T14:59:07Z) - Generative Multimodal Models are In-Context Learners [60.50927925426832]
We introduce Emu2, a generative multimodal model with 37 billion parameters, trained on large-scale multimodal sequences.
Emu2 exhibits strong multimodal in-context learning abilities, even emerging to solve tasks that require on-the-fly reasoning.
arXiv Detail & Related papers (2023-12-20T18:59:58Z) - MMICT: Boosting Multi-Modal Fine-Tuning with In-Context Examples [63.78384552789171]
This paper introduces Multi-Modal In-Context Tuning (MMICT), a novel multi-modal fine-tuning paradigm.
We propose the Multi-Modal Hub (M-Hub), a unified module that captures various multi-modal features according to different inputs and objectives.
Based on M-Hub, MMICT enables MM-LLMs to learn from in-context visual-guided textual features and subsequently generate outputs conditioned on the textual-guided visual features.
arXiv Detail & Related papers (2023-12-11T13:11:04Z) - MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts [92.76662894585809]
We introduce an approach to enhance multimodal models, which we call Multimodal Mixtures of Experts (MMoE)
MMoE is able to be applied to various types of models to gain improvement.
arXiv Detail & Related papers (2023-11-16T05:31:21Z) - Self-MI: Efficient Multimodal Fusion via Self-Supervised Multi-Task
Learning with Auxiliary Mutual Information Maximization [2.4660652494309936]
Multimodal representation learning poses significant challenges.
Existing methods often struggle to exploit the unique characteristics of each modality.
In this study, we propose Self-MI in the self-supervised learning fashion.
arXiv Detail & Related papers (2023-11-07T08:10:36Z) - 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) - Multimodal Prompt Transformer with Hybrid Contrastive Learning for
Emotion Recognition in Conversation [9.817888267356716]
multimodal Emotion Recognition in Conversation (ERC) faces two problems.
Deep emotion cues extraction was performed on modalities with strong representation ability.
Feature filters were designed as multimodal prompt information for modalities with weak representation ability.
MPT embeds multimodal fusion information into each attention layer of the Transformer.
arXiv Detail & Related papers (2023-10-04T13:54:46Z)
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.