Efficient End-to-End Visual Document Understanding with Rationale Distillation

• URL: http://arxiv.org/abs/2311.09612v2
• Date: Tue, 2 Apr 2024 00:11:50 GMT
• Title: Efficient End-to-End Visual Document Understanding with Rationale Distillation
• Authors: Wang Zhu, Alekh Agarwal, Mandar Joshi, Robin Jia, Jesse Thomason, Kristina Toutanova,
• Abstract summary: Rationale Distillation (RD) trains a small student model to predict both rationales and answers. RD outperforms the base model by 4-5% absolute accuracy with only 1% higher computational cost.
• Score: 43.28272448274713
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding visually situated language requires interpreting complex layouts of textual and visual elements. Pre-processing tools, such as optical character recognition (OCR), can map document image inputs to textual tokens, then large language models (LLMs) can reason over text. However, such methods have high computational and engineering complexity. Can small pretrained image-to-text models accurately understand visual documents through similar recognition and reasoning steps instead? We propose Rationale Distillation (RD), which incorporates the outputs of OCR tools, LLMs, and larger multimodal models as intermediate "rationales", and trains a small student model to predict both rationales and answers. On three visual document understanding benchmarks representing infographics, scanned documents, and figures, our Pix2Struct (282M parameters) student model finetuned with RD outperforms the base model by 4-5% absolute accuracy with only 1% higher computational cost.

Related papers

• Éclair -- Extracting Content and Layout with Integrated Reading Order for Documents [7.358946120326249]
  We introduce 'Eclair, a text-extraction tool specifically designed to process a wide range of document types. Given an image, 'Eclair is able to extract formatted text in reading order, along with bounding boxes and their corresponding semantic classes. 'Eclair achieves state-of-the-art accuracy on this benchmark, outperforming other methods across key metrics.
  arXiv  Detail & Related papers  (2025-02-06T17:07:22Z)
• DoPTA: Improving Document Layout Analysis using Patch-Text Alignment [3.3181276611945267]
  We present a novel image-text alignment technique specially designed for leveraging the textual information in document images to improve performance on visual tasks. Our document encoder model DoPTA - trained with this technique demonstrates strong performance on a wide range of document image understanding tasks, without requiring OCR during inference. DoPTA also sets new state-of-the art results on D4LA, and FUNSD, two challenging document visual analysis benchmarks.
  arXiv  Detail & Related papers  (2024-12-17T13:26:31Z)
• LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding [0.0]
  This paper proposes LayoutLLM, a more flexible document analysis method for understanding imaged documents. Existing methods have been developed to enhance document comprehension by incorporating pre-training awareness of images, text, and layout structure. Our experiments demonstrate improvement over the baseline model in various document analysis tasks.
  arXiv  Detail & Related papers  (2024-03-21T09:25:24Z)
• EfficientOCR: An Extensible, Open-Source Package for Efficiently Digitizing World Knowledge [1.8434042562191815]
  EffOCR is a novel open-source optical character recognition (OCR) package. It meets both the computational and sample efficiency requirements for liberating texts at scale. EffOCR is cheap and sample efficient to train, as the model only needs to learn characters' visual appearance and not how they are used in sequence to form language.
  arXiv  Detail & Related papers  (2023-10-16T04:20:16Z)
• UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model [108.85584502396182]
  We propose UReader, a first exploration of universal OCR-free visually-situated language understanding based on the Multimodal Large Language Model (MLLM) By leveraging the shallow text recognition ability of the MLLM, we only finetuned 1.2% parameters. Our single model achieves state-of-the-art ocr-free performance in 8 out of 10 visually-situated language understanding tasks.
  arXiv  Detail & Related papers  (2023-10-08T11:33:09Z)
• mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding [55.4806974284156]
  Document understanding refers to automatically extract, analyze and comprehend information from digital documents, such as a web page. Existing Multi-model Large Language Models (MLLMs) have demonstrated promising zero-shot capabilities in shallow OCR-free text recognition.
  arXiv  Detail & Related papers  (2023-07-04T11:28:07Z)
• Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding [58.70423899829642]
  We present Pix2Struct, a pretrained image-to-text model for purely visual language understanding. We show that a single pretrained model can achieve state-of-the-art results in six out of nine tasks across four domains.
  arXiv  Detail & Related papers  (2022-10-07T06:42:06Z)
• LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking [83.09001231165985]
  We propose LayoutLMv3 to pre-train multimodal Transformers for Document AI with unified text and image masking. The simple unified architecture and training objectives make LayoutLMv3 a general-purpose pre-trained model for both text-centric and image-centric Document AI tasks.
  arXiv  Detail & Related papers  (2022-04-18T16:19:52Z)
• Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision [57.031588264841]
  We leverage a noisy dataset of over one billion image alt-text pairs, obtained without expensive filtering or post-processing steps. A simple dual-encoder architecture learns to align visual and language representations of the image and text pairs using a contrastive loss. We show that the scale of our corpus can make up for its noise and leads to state-of-the-art representations even with such a simple learning scheme.
  arXiv  Detail & Related papers  (2021-02-11T10:08:12Z)

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.