Autoregressive Pre-Training on Pixels and Texts

• URL: http://arxiv.org/abs/2404.10710v3
• Date: Thu, 03 Oct 2024 17:46:40 GMT
• Title: Autoregressive Pre-Training on Pixels and Texts
• Authors: Yekun Chai, Qingyi Liu, Jingwu Xiao, Shuohuan Wang, Yu Sun, Hua Wu,
• Abstract summary: We explore the dual modality of language--both visual and textual--within an autoregressive framework, pre-trained on both document images and texts. Our method employs a multimodal training strategy, utilizing visual data through next patch prediction with a regression head and/or textual data through next token prediction with a classification head. We find that a unidirectional pixel-based model trained solely on visual data can achieve comparable results to state-of-the-art bidirectional models on several language understanding tasks.
• Score: 35.82610192457444
• License:
• Abstract: The integration of visual and textual information represents a promising direction in the advancement of language models. In this paper, we explore the dual modality of language--both visual and textual--within an autoregressive framework, pre-trained on both document images and texts. Our method employs a multimodal training strategy, utilizing visual data through next patch prediction with a regression head and/or textual data through next token prediction with a classification head. We focus on understanding the interaction between these two modalities and their combined impact on model performance. Our extensive evaluation across a wide range of benchmarks shows that incorporating both visual and textual data significantly improves the performance of pixel-based language models. Remarkably, we find that a unidirectional pixel-based model trained solely on visual data can achieve comparable results to state-of-the-art bidirectional models on several language understanding tasks. This work uncovers the untapped potential of integrating visual and textual modalities for more effective language modeling. We release our code, data, and model checkpoints at \url{https://github.com/ernie-research/pixelgpt}.

Related papers

• Enhancing Vision Models for Text-Heavy Content Understanding and Interaction [0.0]
  We build a visual chat application integrating CLIP for image encoding and a model from the Massive Text Embedding Benchmark. The aim of the project is to increase and also enhance the advance vision models' capabilities in understanding complex visual textual data interconnected data.
  arXiv  Detail & Related papers  (2024-05-31T15:17:47Z)
• Visual Analytics for Efficient Image Exploration and User-Guided Image Captioning [35.47078178526536]
  Recent advancements in pre-trained large-scale language-image models have ushered in a new era of visual comprehension. This paper tackles two well-known issues within the realm of visual analytics: (1) the efficient exploration of large-scale image datasets and identification of potential data biases within them; (2) the evaluation of image captions and steering of their generation process.
  arXiv  Detail & Related papers  (2023-11-02T06:21:35Z)
• A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues [23.743431157431893]
  Conditional inference on joint textual and visual clues is a multi-modal reasoning task. We propose a Multi-modal Context Reasoning approach, named ModCR. We conduct extensive experiments on two corresponding data sets and experimental results show significantly improved performance.
  arXiv  Detail & Related papers  (2023-05-08T08:05:40Z)
• ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting [121.11880210592497]
  We argue that the limited capacity of language models comes from 1) implicit language modeling; 2) unidirectional feature representation; and 3) language model with noise input. We propose an autonomous, bidirectional and iterative ABINet++ for scene text spotting.
  arXiv  Detail & Related papers  (2022-11-19T03:50:33Z)
• 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)
• Vision-Language Pre-Training for Boosting Scene Text Detectors [57.08046351495244]
  We specifically adapt vision-language joint learning for scene text detection. We propose to learn contextualized, joint representations through vision-language pre-training. The pre-trained model is able to produce more informative representations with richer semantics.
  arXiv  Detail & Related papers  (2022-04-29T03:53:54Z)
• 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)
• Improving Image Captioning with Better Use of Captions [65.39641077768488]
  We present a novel image captioning architecture to better explore semantics available in captions and leverage that to enhance both image representation and caption generation. Our models first construct caption-guided visual relationship graphs that introduce beneficial inductive bias using weakly supervised multi-instance learning. During generation, the model further incorporates visual relationships using multi-task learning for jointly predicting word and object/predicate tag sequences.
  arXiv  Detail & Related papers  (2020-06-21T14:10:47Z)
• Probing Contextual Language Models for Common Ground with Visual Representations [76.05769268286038]
  We design a probing model that evaluates how effective are text-only representations in distinguishing between matching and non-matching visual representations. Our findings show that language representations alone provide a strong signal for retrieving image patches from the correct object categories. Visually grounded language models slightly outperform text-only language models in instance retrieval, but greatly under-perform humans.
  arXiv  Detail & Related papers  (2020-05-01T21:28:28Z)

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.