MVP: Multi-Stage Vision-Language Pre-Training via Multi-Level Semantic Alignment

• URL: http://arxiv.org/abs/2201.12596v1
• Date: Sat, 29 Jan 2022 14:30:59 GMT
• Title: MVP: Multi-Stage Vision-Language Pre-Training via Multi-Level Semantic Alignment
• Authors: Zejun Li, Zhihao Fan, Huaixiao Tou, Zhongyu Wei
• Abstract summary: We introduce concepts in both modalities to construct two-level semantic representations for language and vision. We train the cross-modality model in two stages, namely, uni-modal learning and cross-modal learning. Our model generates the-state-of-the-art results on several vision and language tasks.
• Score: 24.720485548282845
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we propose a Multi-stage Vision-language Pre-training (MVP) framework to learn cross-modality representation via multi-level semantic alignment. We introduce concepts in both modalities to construct two-level semantic representations for language and vision. Based on the multi-level input, we train the cross-modality model in two stages, namely, uni-modal learning and cross-modal learning. The former stage enforces within-modality interactions to learn multi-level semantics for each single modality. The latter stage enforces interactions across modalities via both coarse-grain and fine-grain semantic alignment tasks. Image-text matching and masked language modeling are then used to further optimize the pre-training model. Our model generates the-state-of-the-art results on several vision and language tasks.

Related papers

• DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention [101.99313208598569]
  Vision-and-language (V-L) tasks require the system to understand both vision content and natural language. We propose DiMBERT (short for Disentangled Multimodal-Attention BERT), which applies separated attention spaces for vision and language. We show that DiMBERT sets new state-of-the-art performance on three tasks.
  arXiv  Detail & Related papers  (2022-10-28T23:00:40Z)
• MAMO: Masked Multimodal Modeling for Fine-Grained Vision-Language Representation Learning [23.45678557013005]
  We propose a jointly masked multimodal modeling method to learn fine-grained multimodal representations. Our method performs joint masking on image-text input and integrates both implicit and explicit targets for the masked signals to recover. Our model achieves state-of-the-art performance on various downstream vision-language tasks, including image-text retrieval, visual question answering, visual reasoning, and weakly-supervised visual grounding.
  arXiv  Detail & Related papers  (2022-10-09T06:31:15Z)
• MaPLe: Multi-modal Prompt Learning [54.96069171726668]
  We propose Multi-modal Prompt Learning (MaPLe) for both vision and language branches to improve alignment between the vision and language representations. Compared with the state-of-the-art method Co-CoOp, MaPLe exhibits favorable performance and achieves an absolute gain of 3.45% on novel classes.
  arXiv  Detail & Related papers  (2022-10-06T17:59:56Z)
• Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training [21.017471684853987]
  We introduce Cross-View Language Modeling, a simple and effective pre-training framework that unifies cross-lingual and cross-modal pre-training. Our approach is motivated by a key observation that cross-lingual and cross-modal pre-training share the same goal of aligning two different views of the same object into a common semantic space. CLM is the first multi-lingual multi-modal pre-trained model that surpasses the translate-test performance of representative English vision-language models by zero-shot cross-lingual transfer.
  arXiv  Detail & Related papers  (2022-06-01T16:45:24Z)
• Single-Stream Multi-Level Alignment for Vision-Language Pretraining [103.09776737512078]
  We propose a single stream model that aligns the modalities at multiple levels. We achieve this using two novel tasks: symmetric cross-modality reconstruction and a pseudo-labeled key word prediction. We demonstrate top performance on a set of Vision-Language downstream tasks such as zero-shot/fine-tuned image/text retrieval, referring expression, and VQA.
  arXiv  Detail & Related papers  (2022-03-27T21:16:10Z)
• UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training [52.852163987208826]
  UC2 is the first machine translation-augmented framework for cross-lingual cross-modal representation learning. We propose two novel pre-training tasks, namely Masked Region-to-Token Modeling (MRTM) and Visual Translation Language Modeling (VTLM) Our proposed framework achieves new state-of-the-art on diverse non-English benchmarks while maintaining comparable performance to monolingual pre-trained models on English tasks.
  arXiv  Detail & Related papers  (2021-04-01T08:30:53Z)
• InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training [135.12061144759517]
  We present an information-theoretic framework that formulates cross-lingual language model pre-training. We propose a new pre-training task based on contrastive learning. By leveraging both monolingual and parallel corpora, we jointly train the pretext to improve the cross-lingual transferability of pre-trained models.
  arXiv  Detail & Related papers  (2020-07-15T16:58:01Z)
• M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training [119.16007395162431]
  M3P is a Multilingual Multimodal Pre-trained model that combines multilingual pre-training and multimodal pre-training. We show that M3P can achieve comparable results for English and new state-of-the-art results for non-English languages.
  arXiv  Detail & Related papers  (2020-06-04T03:54:29Z)

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.