paper-with-me

Papers

CSA: Data-efficient Mapping of Unimodal Features to Multimodal Features

2024-10-10 · Po-han Li, Sandeep P. Chinchali, Ufuk Topcu

Multimodal encoders like CLIP excel in tasks such as zero-shot image classification and cross-modal retrieval. However, they require excessive training data. We propose canonical similarity analysis (CSA), which uses two unimodal encoders to replicate multimodal encoders using limited data. CSA maps unimodal features into a multimodal space, using a new similarity score to retain only the multimodal information. CSA only involves the inference of unimodal encoders and a cubic-complexity matrix decomposition, eliminating the need for extensive GPU-based model training. Experiments show that CSA outperforms CLIP while requiring $50,000\times$ fewer multimodal data pairs to bridge the modalities given pre-trained unimodal encoders on ImageNet classification and misinformative news caption detection. CSA surpasses the state-of-the-art method to map unimodal features to multimodal features. We also demonstrate the ability of CSA with modalities beyond image and text, paving the way for future modality pairs with limited paired multimodal data but abundant unpaired unimodal data, such as lidar and text.

📄 PDF Abstract BibTeX arXiv:2410.07610

Code (0)

등록된 구현이 없습니다.

Tasks

Cross-Modal RetrievalGPUimage-classificationImage ClassificationZero-Shot Image Classification

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Mind the Gap: Aligning the Brain with Language Models Requires a Nonlinear and Multimodal Approach

2025-02-18 · Danny Dongyeop Han, Yunju Cho, Jiook Cha, Jay-Yoon Lee

Self-supervised language and audio models effectively predict brain responses to speech. However, traditional prediction models rely on linear mappings from unimodal features, despite the complex integration of auditory …

Prediction

Lightweight Models for Multimodal Sequential Data

2021-04-01 · EACL (WASSA) 2021 4 · Soumya Sourav, Jessica Ouyang

Human language encompasses more than just text; it also conveys emotions through tone and gestures. We present a case study of three simple and efficient Transformer-based architectures for predicting sentiment and emoti…

Multimodal Sentiment AnalysisSentiment Analysis

Meta-Learn Unimodal Signals with Weak Supervision for Multimodal Sentiment Analysis

2024-08-28 · Sijie Mai, Yu Zhao, Ying Zeng, Jianhua Yao 외

Multimodal sentiment analysis aims to effectively integrate information from various sources to infer sentiment, where in many cases there are no annotations for unimodal labels. Therefore, most works rely on multimodal …

DenoisingMultimodal Sentiment AnalysisSentiment Analysis

UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning

2023-05-16 · Heqing Zou, Meng Shen, Chen Chen, Yuchen Hu 외

Multimodal learning aims to imitate human beings to acquire complementary information from multiple modalities for various downstream tasks. However, traditional aggregation-based multimodal fusion methods ignore the int…

Contrastive LearningImage-text Classificationtext-classificationText Classification

Expanding Large Pre-Trained Unimodal Models With Multimodal Information Injection for Image-Text Multimodal Classification

2022-01-01 · CVPR 2022 1 · Tao Liang, Guosheng Lin, Mingyang Wan, Tianrui Li 외

Fine-tuning pre-trained models for downstream tasks is mainstream in deep learning. However, the pre-trained models are limited to be fine-tuned by data from a specific modality. For example, as a visual model, Dense…