paper-with-me

Papers

Extending Multi-modal Contrastive Representations

2023-10-13 · Zehan Wang, Ziang Zhang, Luping Liu, Yang Zhao, Haifeng Huang, Tao Jin, Zhou Zhao

Multi-modal contrastive representation (MCR) of more than three modalities is critical in multi-modal learning. Although recent methods showcase impressive achievements, the high dependence on large-scale, high-quality paired data and the expensive training costs limit their further development. Inspired by recent C-MCR, this paper proposes Extending Multimodal Contrastive Representation (Ex-MCR), a training-efficient and paired-data-free method to flexibly learn unified contrastive representation space for more than three modalities by integrating the knowledge of existing MCR spaces. Specifically, Ex-MCR aligns multiple existing MCRs into the same based MCR, which can effectively preserve the original semantic alignment of the based MCR. Besides, we comprehensively enhance the entire learning pipeline for aligning MCR spaces from the perspectives of training data, architecture, and learning objectives. With the preserved original modality alignment and the enhanced space alignment, Ex-MCR shows superior representation learning performance and excellent modality extensibility. To demonstrate the effectiveness of Ex-MCR, we align the MCR spaces of CLAP (audio-text) and ULIP (3D-vision) into the CLIP (vision-text), leveraging the overlapping text and image modality, respectively. Remarkably, without using any paired data, Ex-MCR learns a 3D-image-text-audio unified contrastive representation, and it achieves state-of-the-art performance on audio-visual, 3D-image, audio-text, visual-text retrieval, and 3D object classification tasks. More importantly, extensive qualitative results further demonstrate the emergent semantic alignment between the extended modalities (e.g., audio and 3D), which highlights the great potential of modality extensibility.

📄 PDF Abstract BibTeX arXiv:2310.08884

Code (1)

mcr-peft/ex-mcr 공식 구현 pytorch

Tasks

3D Object ClassificationRepresentation LearningText Retrieval

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
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

OmniDRCA: Parallel Speech-Text Foundation Model via Dual-Resolution Speech Representations and Contrastive Alignment

2025-06-11 · Chao-Hong Tan, Qian Chen, Wen Wang, Chong Deng 외

Recent studies on end-to-end speech generation with large language models (LLMs) have attracted significant community attention, with multiple works extending text-based LLMs to generate discrete speech tokens. Existing …

cross-modal alignmentQuestion AnsweringSpeech SynthesisText Generation

Contrastive Learning of Visual-Semantic Embeddings

2021-10-17 · Anurag Jain, Yashaswi Verma

Contrastive learning is a powerful technique to learn representations that are semantically distinctive and geometrically invariant. While most of the earlier approaches have demonstrated its effectiveness on single-moda…

Contrastive Learningimage-classificationImage ClassificationImage Retrieval+2

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM

2025-07-28 · Shen Li, Liuyi Yao, Wujia Niu, Lan Zhang 외 arxiv

Large visual-language models (LVLMs) integrate aligned large language models (LLMs) with visual modules to process multimodal inputs. However, the safety mechanisms developed for text-based LLMs do not naturally extend t…

CLIP-RL: Aligning Language and Policy Representations for Task Transfer in Reinforcement Learning

2025-12-01 · Chainesh Gautam, Raghuram Bharadwaj Diddigi arxiv

Recently, there has been an increasing need to develop agents capable of solving multiple tasks within the same environment, especially when these tasks are naturally associated with language. In this work, we propose a …

Reinforcement Learning

Improving the Modality Representation with Multi-View Contrastive Learning for Multimodal Sentiment Analysis

2022-10-28 · Peipei Liu, Xin Zheng, Hong Li, Jie Liu 외

Modality representation learning is an important problem for multimodal sentiment analysis (MSA), since the highly distinguishable representations can contribute to improving the analysis effect. Previous works of MSA ha…

Contrastive LearningMultimodal Sentiment AnalysisRepresentation LearningSentiment Analysis