A Simple Data Augmentation Strategy for Text-in-Image Scientific VQA

• URL: http://arxiv.org/abs/2509.20119v1
• Date: Wed, 24 Sep 2025 13:41:04 GMT
• Title: A Simple Data Augmentation Strategy for Text-in-Image Scientific VQA
• Authors: Belal Shoer, Yova Kementchedjhieva,
• Abstract summary: Fine-tuning a small multilingual multimodal model on a mix of our synthetic data and EXAMS-V yields notable gains across 13 languages.<n>This paper introduces a new paradigm by embedding both visual and textual content into a single image.<n>To address the scarcity of training data in this "text-in-image" format, we synthesize a new dataset by converting existing separate image-text pairs into unified images.
• Score: 4.456773511251556
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Scientific visual question answering poses significant challenges for vision-language models due to the complexity of scientific figures and their multimodal context. Traditional approaches treat the figure and accompanying text (e.g., questions and answer options) as separate inputs. EXAMS-V introduced a new paradigm by embedding both visual and textual content into a single image. However, even state-of-the-art proprietary models perform poorly on this setup in zero-shot settings, underscoring the need for task-specific fine-tuning. To address the scarcity of training data in this "text-in-image" format, we synthesize a new dataset by converting existing separate image-text pairs into unified images. Fine-tuning a small multilingual multimodal model on a mix of our synthetic data and EXAMS-V yields notable gains across 13 languages, demonstrating strong average improvements and cross-lingual transfer.

Related papers

• Towards Visual Text Grounding of Multimodal Large Language Model [74.22413337117617]
  We introduce TRIG, a novel task with a newly designed instruction dataset for benchmarking text-rich image grounding.<n>Specifically, we propose an OCR-LLM-human interaction pipeline to create 800 manually annotated question-answer pairs as a benchmark.<n>A comprehensive evaluation of various MLLMs on our proposed benchmark exposes substantial limitations in their grounding capability on text-rich images.
  arXiv  Detail & Related papers  (2025-04-07T12:01:59Z)
• Debiasing Vison-Language Models with Text-Only Training [15.069736314663352]
  We propose a Text-Only Debiasing framework called TOD, leveraging a text-as-image training paradigm to mitigate visual biases. To address the limitations, we propose a Text-Only Debiasing framework called TOD, leveraging a text-as-image training paradigm to mitigate visual biases.
  arXiv  Detail & Related papers  (2024-10-12T04:34:46Z)
• Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks [62.758680527838436]
  We propose Leopard, an MLLM tailored for handling vision-language tasks involving multiple text-rich images.<n>First, we curated about one million high-quality multimodal instruction-tuning data, tailored to text-rich, multi-image scenarios.<n>Second, we proposed an adaptive high-resolution multi-image encoding module to dynamically optimize the allocation of visual sequence length.
  arXiv  Detail & Related papers  (2024-10-02T16:55:01Z)
• Translatotron-V(ison): An End-to-End Model for In-Image Machine Translation [81.45400849638347]
  In-image machine translation (IIMT) aims to translate an image containing texts in source language into an image containing translations in target language. In this paper, we propose an end-to-end IIMT model consisting of four modules. Our model achieves competitive performance compared to cascaded models with only 70.9% of parameters, and significantly outperforms the pixel-level end-to-end IIMT model.
  arXiv  Detail & Related papers  (2024-07-03T08:15:39Z)
• TRINS: Towards Multimodal Language Models that Can Read [61.17806538631744]
  TRINS is a Text-Rich image INStruction dataset. It contains 39,153 text-rich images, captions, and 102,437 questions. We introduce a Language-vision Reading Assistant (LaRA) which is good at understanding textual content within images.
  arXiv  Detail & Related papers  (2024-06-10T18:52:37Z)
• FINEMATCH: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction [66.98008357232428]
  We propose FineMatch, a new aspect-based fine-grained text and image matching benchmark. FineMatch focuses on text and image mismatch detection and correction. We show that models trained on FineMatch demonstrate enhanced proficiency in detecting fine-grained text and image mismatches.
  arXiv  Detail & Related papers  (2024-04-23T03:42:14Z)
• Text Data-Centric Image Captioning with Interactive Prompts [20.48013600818985]
  Supervised image captioning approaches have made great progress, but it is challenging to collect high-quality human-annotated image-text data. This paper proposes a new Text data-centric approach with Interactive Prompts for image Captioning, named TIPCap.
  arXiv  Detail & Related papers  (2024-03-28T07:43:49Z)
• Synth$^2$: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings [16.28853186016663]
  We create synthetic image-text pairs for efficient and effective Visual-Language Models (VLMs) training. Our method employs a pretrained text-to-image model to synthesize image embeddings from captions generated by an LLM. Our VLM, finetuned on synthetic data achieves comparable performance to models trained solely on human-annotated data.
  arXiv  Detail & Related papers  (2024-03-12T15:36:42Z)
• COSA: Concatenated Sample Pretrained Vision-Language Foundation Model [78.32081709802873]
  Most vision-language foundation models employ image-text datasets for pretraining. We propose COSA, a COncatenated SAmple pretrained vision-language foundation model. We achieve this by sequentially concatenating multiple image-text pairs as inputs for pretraining. This transformation effectively converts existing image-text corpora into a pseudo long-form video-paragraph corpus.
  arXiv  Detail & Related papers  (2023-06-15T12:29:42Z)
• ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training [29.240131406803794]
  We show that a common space can be created without any training at all, using single-domain encoders and a much smaller amount of image-text pairs. Our model has unique properties, most notably, deploying a new version with updated training samples can be done in a matter of seconds.
  arXiv  Detail & Related papers  (2022-10-04T16:56:22Z)
• 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)

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.