ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models

• URL: http://arxiv.org/abs/2412.07012v3
• Date: Sun, 29 Dec 2024 03:52:23 GMT
• Title: ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models
• Authors: Jieyu Zhang, Le Xue, Linxin Song, Jun Wang, Weikai Huang, Manli Shu, An Yan, Zixian Ma, Juan Carlos Niebles, Silvio Savarese, Caiming Xiong, Zeyuan Chen, Ranjay Krishna, Ran Xu,
• Abstract summary: Existing practices rely on powerful but costly large language models (LLMs) or multimodal language models (MLMs) to produce instruction data.<n>We present a programmatic approach that employs scene graphs as symbolic representations of images and human-written programs to systematically synthesize vision-centric instruction data.<n>Our approach ensures the interpretability and controllability of the data generation process and scales efficiently while maintaining factual accuracy.
• Score: 103.25208095165486
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the rise of multimodal applications, instruction data has become critical for training multimodal language models capable of understanding complex image-based queries. Existing practices rely on powerful but costly large language models (LLMs) or multimodal language models (MLMs) to produce instruction data. These are often prone to hallucinations, licensing issues and the generation process is often hard to scale and interpret. In this work, we present a programmatic approach that employs scene graphs as symbolic representations of images and human-written programs to systematically synthesize vision-centric instruction data. Our approach ensures the interpretability and controllability of the data generation process and scales efficiently while maintaining factual accuracy. By implementing a suite of 24 single-image, 14 multi-image instruction generators, and a scene graph generation pipeline, we build a scalable, cost-effective system: ProVision which produces diverse question-answer pairs concerning objects, attributes, relations, depth, etc., for any given image. Applied to Visual Genome and DataComp datasets, we generate over 10 million instruction data points, ProVision-10M, and leverage them in both pretraining and instruction tuning stages of MLMs. When adopted in the instruction tuning stage, our single-image instruction data yields up to a 7% improvement on the 2D split and 8% on the 3D split of CVBench, along with a 3% increase in performance on QBench2, RealWorldQA, and MMMU. Our multi-image instruction data leads to an 8% improvement on Mantis-Eval. Incorporation of our data in both pre-training and fine-tuning stages of xGen-MM-4B leads to an averaged improvement of 1.6% across 11 benchmarks.

Related papers

• Picking the Cream of the Crop: Visual-Centric Data Selection with Collaborative Agents [62.616106562146776]
  We propose a textbfVisual-Centric textbfSelection approach via textbfAgents Collaboration (ViSA) Our approach consists of 1) an image information quantification method via visual agents collaboration to select images with rich visual information, and 2) a visual-centric instruction quality assessment method to select high-quality instruction data related to high-quality images.
  arXiv  Detail & Related papers  (2025-02-27T09:37:30Z)
• MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct [148.39859547619156]
  We propose MMEvol, a novel multimodal instruction data evolution framework. MMEvol iteratively improves data quality through a refined combination of fine-grained perception, cognitive reasoning, and interaction evolution. Our approach reaches state-of-the-art (SOTA) performance in nine tasks using significantly less data compared to state-of-the-art models.
  arXiv  Detail & Related papers  (2024-09-09T17:44:00Z)
• Generative Visual Instruction Tuning [11.727612242016871]
  We propose to use automatically generated instruction-following data to improve the zero-shot capabilities of a large multimodal model. We produce GenLLaVA, a Generative Large Language and Visual Assistant. Our model demonstrates visual understanding capabilities superior to LLaVA and demonstrates competitive results with native multimodal models.
  arXiv  Detail & Related papers  (2024-06-17T07:06:58Z)
• Instruction-Guided Visual Masking [25.26544571379426]
  Instruction-guided Visual Masking (IVM) is a versatile visual grounding model that is compatible with diverse multimodal models. IVM-enhanced multimodal models can effectively focus on task-relevant image regions to better align with complex instructions.
  arXiv  Detail & Related papers  (2024-05-30T07:48:32Z)
• Enhancing Large Vision Language Models with Self-Training on Image Comprehension [131.14381425260706]
  We introduce Self-Training on Image (STIC), which emphasizes a self-training approach specifically for image comprehension. First, the model self-constructs a preference for image descriptions using unlabeled images. To further self-improve reasoning on the extracted visual information, we let the model reuse a small portion of existing instruction-tuning data.
  arXiv  Detail & Related papers  (2024-05-30T05:53:49Z)
• Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want [58.091825321168514]
  We present the Draw-and-Understand framework, exploring how to integrate visual prompting understanding capabilities into Multimodal Large Language Models (MLLMs) Visual prompts allow users to interact through multi-modal instructions, enhancing the models' interactivity and fine-grained image comprehension. In this framework, we propose a general architecture adaptable to different pre-trained MLLMs, enabling it to recognize various types of visual prompts.
  arXiv  Detail & Related papers  (2024-03-29T16:26:20Z)
• MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training [103.72844619581811]
  We build performant Multimodal Large Language Models (MLLMs) In particular, we study the importance of various architecture components and data choices. We demonstrate that for large-scale multimodal pre-training using a careful mix of image-caption, interleaved image-text, and text-only data.
  arXiv  Detail & Related papers  (2024-03-14T17:51:32Z)
• Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs [49.88461345825586]
  This paper proposes a new framework to enhance the fine-grained image understanding abilities of MLLMs. We present a new method for constructing the instruction tuning dataset at a low cost by leveraging annotations in existing datasets. We show that our model exhibits a 5.2% accuracy improvement over Qwen-VL and surpasses the accuracy of Kosmos-2 by 24.7%.
  arXiv  Detail & Related papers  (2023-10-01T05:53:15Z)
• SVIT: Scaling up Visual Instruction Tuning [26.794950789335402]
  We build a dataset of 4.2 million visual instruction tuning data including 1.6M conversation question-answer (QA) pairs, 1.6M complex reasoning QA pairs, 1.0M referring QA pairs and 106K detailed image descriptions. Experiments verify that SVIT-v1.5, trained on the proposed dataset, outperforms state-of-the-art Multimodal Large Language Models on popular benchmarks.
  arXiv  Detail & Related papers  (2023-07-09T03:25:14Z)

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.