InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining

• URL: http://arxiv.org/abs/2003.13198v4
• Date: Thu, 22 Apr 2021 11:20:26 GMT
• Title: InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining
• Authors: Junyang Lin, An Yang, Yichang Zhang, Jie Liu, Jingren Zhou, Hongxia Yang
• Abstract summary: We propose a novel model, namely InterBERT (BERT for Interaction), which is the first model of our series of multimodal pretraining methods M6. The model owns strong capability of modeling interaction between the information flows of different modalities. We propose a large-scale dataset for multi-modal pretraining in Chinese, and we develop the Chinese InterBERT which is the first Chinese multi-modal pretrained model.
• Score: 76.32065400614162
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-modal pretraining for learning high-level multi-modal representation is a further step towards deep learning and artificial intelligence. In this work, we propose a novel model, namely InterBERT (BERT for Interaction), which is the first model of our series of multimodal pretraining methods M6 (MultiModality-to-MultiModality Multitask Mega-transformer). The model owns strong capability of modeling interaction between the information flows of different modalities. The single-stream interaction module is capable of effectively processing information of multiple modalilties, and the two-stream module on top preserves the independence of each modality to avoid performance downgrade in single-modal tasks. We pretrain the model with three pretraining tasks, including masked segment modeling (MSM), masked region modeling (MRM) and image-text matching (ITM); and finetune the model on a series of vision-and-language downstream tasks. Experimental results demonstrate that InterBERT outperforms a series of strong baselines, including the most recent multi-modal pretraining methods, and the analysis shows that MSM and MRM are effective for pretraining and our method can achieve performances comparable to BERT in single-modal tasks. Besides, we propose a large-scale dataset for multi-modal pretraining in Chinese, and we develop the Chinese InterBERT which is the first Chinese multi-modal pretrained model. We pretrain the Chinese InterBERT on our proposed dataset of 3.1M image-text pairs from the mobile Taobao, the largest Chinese e-commerce platform. We finetune the model for text-based image retrieval, and recently we deployed the model online for topic-based recommendation.

Related papers

• NVLM: Open Frontier-Class Multimodal LLMs [64.00053046838225]
  We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks. We propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. We develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks.
  arXiv  Detail & Related papers  (2024-09-17T17:59:06Z)
• S3: A Simple Strong Sample-effective Multimodal Dialog System [61.31055673156622]
  We present a conceptually simple yet powerful baseline for the multimodal dialog task, an S3 model, that achieves near state-of-the-art results. The system is based on a pre-trained large language model, pre-trained modality encoders for image and audio, and a trainable modality projector.
  arXiv  Detail & Related papers  (2024-06-26T12:45:43Z)
• Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal Assistants [65.47222691674074]
  Muffin framework employs pre-trained vision-language models to act as providers of visual signals. UniMM-Chat dataset explores the complementarities of datasets to generate 1.1M high-quality and diverse multimodal instructions.
  arXiv  Detail & Related papers  (2023-10-01T12:35:18Z)
• On Uni-Modal Feature Learning in Supervised Multi-Modal Learning [21.822251958013737]
  We abstract the features (i.e. learned representations) of multi-modal data into 1) uni-modal features, which can be learned from uni-modal training, and 2) paired features, which can only be learned from cross-modal interactions. We demonstrate that, under a simple guiding strategy, we can achieve comparable results to other complex late-fusion or intermediate-fusion methods on various multi-modal datasets.
  arXiv  Detail & Related papers  (2023-05-02T07:15:10Z)
• MoMo: A shared encoder Model for text, image and multi-Modal representations [4.812718493682455]
  We propose a self-supervised shared encoder model that achieves strong results on several visual, language and multimodal benchmarks. We use a single transformer with all the encoder layers processing both the text and the image modalities.
  arXiv  Detail & Related papers  (2023-04-11T22:26:10Z)
• eP-ALM: Efficient Perceptual Augmentation of Language Models [70.47962271121389]
  We propose to direct effort to efficient adaptations of existing models, and propose to augment Language Models with perception. Existing approaches for adapting pretrained models for vision-language tasks still rely on several key components that hinder their efficiency. We show that by freezing more than 99% of total parameters, training only one linear projection layer, and prepending only one trainable token, our approach (dubbed eP-ALM) significantly outperforms other baselines on VQA and Captioning.
  arXiv  Detail & Related papers  (2023-03-20T19:20:34Z)
• Multimodal Contrastive Learning via Uni-Modal Coding and Cross-Modal Prediction for Multimodal Sentiment Analysis [19.07020276666615]
  We propose a novel framework named MultiModal Contrastive Learning (MMCL) for multimodal representation to capture intra- and inter-modality dynamics simultaneously. We also design two contrastive learning tasks, instance- and sentiment-based contrastive learning, to promote the process of prediction and learn more interactive information related to sentiment.
  arXiv  Detail & Related papers  (2022-10-26T08:24:15Z)
• Knowledge Perceived Multi-modal Pretraining in E-commerce [12.012793707741562]
  Current multi-modal pretraining methods for image and text modalities lack robustness in the face of modality-missing and modality-noise. We propose K3M, which introduces knowledge modality in multi-modal pretraining to correct the noise and supplement the missing of image and text modalities.
  arXiv  Detail & Related papers  (2021-08-20T08:01:28Z)
• WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training [71.37731379031487]
  We propose a two-tower pre-training model called BriVL within the cross-modal contrastive learning framework. Unlike OpenAI CLIP that adopts a simple contrastive learning method, we devise a more advanced algorithm by adapting the latest method MoCo into the cross-modal scenario. By building a large queue-based dictionary, our BriVL can incorporate more negative samples in limited GPU resources.
  arXiv  Detail & Related papers  (2021-03-11T09:39:49Z)

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.