VisCon-100K: Leveraging Contextual Web Data for Fine-tuning Vision Language Models

• URL: http://arxiv.org/abs/2502.10250v1
• Date: Fri, 14 Feb 2025 15:59:33 GMT
• Title: VisCon-100K: Leveraging Contextual Web Data for Fine-tuning Vision Language Models
• Authors: Gokul Karthik Kumar, Iheb Chaabane, Kebin Wu,
• Abstract summary: We introduce VisCon-100K, a novel dataset derived from interleaved image-text web documents. Our approach transforms 45K web documents from the OBELICS dataset into 100K image conversation samples. We utilize GPT-4V to generate image-contextual captions and OpenChat 3.5 model to convert these captions into diverse free-form and multiple-choice question-answer pairs.
• Score: 0.351124620232225
• License:
• Abstract: Vision-language models (VLMs) excel in various visual benchmarks but are often constrained by the lack of high-quality visual fine-tuning data. To address this challenge, we introduce VisCon-100K, a novel dataset derived from interleaved image-text web documents. Our approach transforms 45K web documents from the OBELICS dataset into 100K image conversation samples. We utilize GPT-4V to generate image-contextual captions and OpenChat 3.5 model to convert these captions into diverse free-form and multiple-choice question-answer pairs. Integrating this dataset for fine-tuning considerably enhances VLM performance across multiple benchmarks. Unlike methods that focus solely on fine-grained visual content, our approach leverages accompanying web context, yielding superior results. We also discover that a `leaky modality mix,' where conversation samples contain questions answerable from both the image and its contextual caption, outperforms non-leaky combinations of captions and Q\&A pairs. VisCon-100k dataset shows strong performance with two popular VLM approaches: text-only large language model (LLM) aligned with a vision encoder using image captions data (ShareGPT4V-7b) and multimodally pretrained LLM (IDEFICS2-8b) using interleaved image-text data. In addition to releasing the VisCon-100K dataset, we provide a contextual captioner trained on this dataset, facilitating scalable fine-tuning data generation for future research and open-source applications. Using the same pipeline, but substituting our trained contextual captioner for GPT-4V, we also release the larger VisCon-1M dataset.

Related papers

• AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding [96.01726275876548]
  We present AdaptVision, a multimodal large language model specifically designed to dynamically process input images at varying resolutions. We devise a dynamic image partitioning module that adjusts the number of visual tokens according to the size and aspect ratio of images. Our model is capable of processing images with resolutions up to $1008times 1008$.
  arXiv  Detail & Related papers  (2024-08-30T03:16:49Z)
• RETTA: Retrieval-Enhanced Test-Time Adaptation for Zero-Shot Video Captioning [69.23782518456932]
  We propose a novel zero-shot video captioning framework named Retrieval-Enhanced Test-Time Adaptation (RETTA) We bridge video and text using four key models: a general video-text retrieval model XCLIP, a general image-text matching model CLIP, a text alignment model AnglE, and a text generation model GPT-2. To address this problem, we propose using learnable tokens as a communication medium among these four frozen models GPT-2, XCLIP, CLIP, and AnglE.
  arXiv  Detail & Related papers  (2024-05-11T16:22:00Z)
• 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)
• MLLMs-Augmented Visual-Language Representation Learning [70.5293060238008]
  We demonstrate that Multi-modal Large Language Models (MLLMs) can enhance visual-language representation learning. Our approach is simple, utilizing MLLMs to extend multiple diverse captions for each image. We propose "text shearing" to maintain the quality and availability of extended captions.
  arXiv  Detail & Related papers  (2023-11-30T18:05:52Z)
• Sieve: Multimodal Dataset Pruning Using Image Captioning Models [11.362835828985494]
  Vision-Language Models (VLMs) are pretrained on large, diverse, and noisy web-crawled datasets. We argue that this approach suffers from multiple limitations including false positives and negatives due to CLIP's pretraining on noisy labels. We propose a pruning signal, Sieve, that employs synthetic captions generated by image-captioning models pretrained on small, diverse, and well-aligned image-text pairs.
  arXiv  Detail & Related papers  (2023-10-03T14:53:53Z)
• Improving Multimodal Datasets with Image Captioning [65.74736570293622]
  We study how generated captions can increase the utility of web-scraped datapoints with nondescript text. Our experiments with using generated captions at DataComp's large scale (1.28B image-text pairs) offer insights into the limitations of synthetic text.
  arXiv  Detail & Related papers  (2023-07-19T17:47:12Z)
• LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding [85.39419609430453]
  This work enhances the current visual instruction tuning pipeline with text-rich images. We first use publicly available OCR tools to collect results on 422K text-rich images from the LAION dataset. We prompt text-only GPT-4 with recognized texts and image captions to generate 16K conversations, each containing question-answer pairs for text-rich images.
  arXiv  Detail & Related papers  (2023-06-29T17:08:16Z)
• OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents [122.55393759474181]
  We introduce OBELICS, an open web-scale filtered dataset of interleaved image-text documents. We describe the dataset creation process, present comprehensive filtering rules, and provide an analysis of the dataset's content. We train vision and language models of 9 and 80 billion parameters named IDEFICS, and obtain competitive performance on different multimodal benchmarks.
  arXiv  Detail & Related papers  (2023-06-21T14:01:01Z)
• CLIP4Caption: CLIP for Video Caption [9.470254059503862]
  We propose a CLIP4Caption framework that improves video captioning based on a CLIP-enhanced video-text matching network (VTM) This framework is taking full advantage of the information from both vision and language and enforcing the model to learn strongly text-correlated video features for text generation.
  arXiv  Detail & Related papers  (2021-10-13T10:17:06Z)

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.