paper-with-me

홈 › Papers

Mixture-of-Prompt-Experts for Multi-modal Semantic Understanding

2024-03-17 · Zichen Wu, Hsiu-Yuan Huang, Fanyi Qu, Yunfang Wu

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.

📄 PDF Abstract BibTeX arXiv:2403.11311

Code (0)

등록된 구현이 없습니다.

Tasks

Few-Shot LearningLanguage ModellingSarcasm DetectionSentiment Analysis

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

WMoE-CLIP: Wavelet-Enhanced Mixture-of-Experts Prompt Learning for Zero-Shot Anomaly Detection

2026-03-06 · Peng Chen, Chao Huang arxiv

Vision-language models have recently shown strong generalization in zero-shot anomaly detection (ZSAD), enabling the detection of unseen anomalies without task-specific supervision. However, existing approaches typically…

Anomaly Detection

M$^4$-SAM: Multi-Modal Mixture-of-Experts with Memory-Augmented SAM for RGB-D Video Salient Object Detection

2026-05-12 · Jiyuan Liu, Jia Lin, Xiaofei Zhou, Runmin Cong 외 arxiv

The Segment Anything Model 2 (SAM2) has emerged as a foundation model for universal segmentation. Owing to its generalizable visual representations, SAM2 has been successfully applied to various downstream tasks. However…

Video Salient Object Detection

MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion

2024-03-14 · Ruixiang Jiang, Lingbo Liu, Changwen Chen

Despite the demonstrated parameter efficiency of prompt-based multimodal fusion methods, their limited adaptivity and expressiveness often result in suboptimal performance compared to other tuning approaches. In this pap…

DisentanglementMultimodal Deep LearningVisual Entailment

MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion

2026-07-17 · Xu Hou, Meiyu Liang, Wei Huang, Yawen Li 외 arxiv

Multimodal Knowledge Graph Completion (MKGC) requires inferring missing entities from structural, textual, and visual cues. Existing diffusion-based MKGC methods usually denoise directly on raw multimodal features. Such …

Knowledge Graph Completion

BiPrompt-SAM: Enhancing Image Segmentation via Explicit Selection between Point and Text Prompts

2025-03-25 · Suzhe Xu, Jialin Peng, ChengYuan Zhang

Segmentation is a fundamental task in computer vision, with prompt-driven methods gaining prominence due to their flexibility. The recent Segment Anything Model (SAM) has demonstrated powerful point-prompt segmentation c…

Image SegmentationMixture-of-ExpertsSegmentationSemantic Segmentation