Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks

• URL: http://arxiv.org/abs/2208.10442v1
• Date: Mon, 22 Aug 2022 16:55:04 GMT
• Title: Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks
• Authors: Wenhui Wang, Hangbo Bao, Li Dong, Johan Bjorck, Zhiliang Peng, Qiang Liu, Kriti Aggarwal, Owais Khan Mohammed, Saksham Singhal, Subhojit Som, Furu Wei
• Abstract summary: We introduce a general-purpose multimodal foundation model BEiT-3. It achieves state-of-the-art transfer performance on both vision and vision-language tasks.
• Score: 87.6494641931349
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A big convergence of language, vision, and multimodal pretraining is emerging. In this work, we introduce a general-purpose multimodal foundation model BEiT-3, which achieves state-of-the-art transfer performance on both vision and vision-language tasks. Specifically, we advance the big convergence from three aspects: backbone architecture, pretraining task, and model scaling up. We introduce Multiway Transformers for general-purpose modeling, where the modular architecture enables both deep fusion and modality-specific encoding. Based on the shared backbone, we perform masked "language" modeling on images (Imglish), texts (English), and image-text pairs ("parallel sentences") in a unified manner. Experimental results show that BEiT-3 obtains state-of-the-art performance on object detection (COCO), semantic segmentation (ADE20K), image classification (ImageNet), visual reasoning (NLVR2), visual question answering (VQAv2), image captioning (COCO), and cross-modal retrieval (Flickr30K, COCO).

Related papers

• mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models [71.40705814904898]
  We introduce the versatile multi-modal large language model, mPLUG-Owl3, which enhances the capability for long image-sequence understanding. Specifically, we propose novel hyper attention blocks to efficiently integrate vision and language into a common language-guided semantic space.
  arXiv  Detail & Related papers  (2024-08-09T03:25:42Z)
• Dense Multimodal Alignment for Open-Vocabulary 3D Scene Understanding [39.55810156545949]
  We propose a Multimodal Alignment (DMA) framework to densely co-embed different modalities into a common space. Our DMA method produces highly competitive open-vocabulary segmentation performance on various indoor and outdoor tasks.
  arXiv  Detail & Related papers  (2024-07-13T05:39:17Z)
• Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning [115.50132185963139]
  CM3Leon is a decoder-only multi-modal language model capable of generating and infilling both text and images. It is the first multi-modal model trained with a recipe adapted from text-only language models. CM3Leon achieves state-of-the-art performance in text-to-image generation with 5x less training compute than comparable methods.
  arXiv  Detail & Related papers  (2023-09-05T21:27:27Z)
• A Survey of Vision-Language Pre-training from the Lens of Multimodal Machine Translation [13.426403221815063]
  This paper surveys the landscape of language-and-vision pre-training from the lens of multimodal machine translation. We summarize the common architectures, pre-training objectives, and datasets from literature and conjecture what further is needed to make progress on multimodal machine translation.
  arXiv  Detail & Related papers  (2023-06-12T15:56:10Z)
• mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video [89.19867891570945]
  mPLUG-2 is a new unified paradigm with modularized design for multi-modal pretraining. It shares common universal modules for modality collaboration and disentangling different modality modules to deal with modality entanglement. It is flexible to select different modules for different understanding and generation tasks across all modalities including text, image, and video.
  arXiv  Detail & Related papers  (2023-02-01T12:40:03Z)
• On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization [89.94078728495423]
  We show that recent advances in each modality, CLIP image representations and scaling of language models, do not consistently improve multimodal self-rationalization of tasks with multimodal inputs. Our findings call for a backbone modelling approach that can be built on to advance text generation from images and text beyond image captioning.
  arXiv  Detail & Related papers  (2022-05-24T00:52:40Z)
• 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)
• All-in-One Image-Grounded Conversational Agents [31.28974522911758]
  We design an architecture that combines state-of-the-art Transformer and ResNeXt modules fed into a novel attentive multimodal module. We provide a thorough analysis of the components of the model, and transfer performance when training on one, some, or all of the tasks.
  arXiv  Detail & Related papers  (2019-12-28T03:51:52Z)

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.