ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models

• URL: http://arxiv.org/abs/2402.11684v2
• Date: Mon, 17 Jun 2024 07:55:59 GMT
• Title: ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models
• Authors: Guiming Hardy Chen, Shunian Chen, Ruifei Zhang, Junying Chen, Xiangbo Wu, Zhiyi Zhang, Zhihong Chen, Jianquan Li, Xiang Wan, Benyou Wang,
• Abstract summary: Large vision-language models (LVLMs) have shown premise in a broad range of vision-language tasks with their strong reasoning and generalization capabilities. This study aims to bridge the performance gap between traditional-scale LVLMs and resource-friendly lite versions by adopting high-quality training data.
• Score: 45.040292339670096
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large vision-language models (LVLMs) have shown premise in a broad range of vision-language tasks with their strong reasoning and generalization capabilities. However, they require considerable computational resources for training and deployment. This study aims to bridge the performance gap between traditional-scale LVLMs and resource-friendly lite versions by adopting high-quality training data. To this end, we propose a comprehensive pipeline for generating a synthetic dataset. The key idea is to leverage strong proprietary models to generate (i) fine-grained image annotations for vision-language alignment and (ii) complex reasoning visual question-answering pairs for visual instruction fine-tuning, yielding 1.3M samples in total. We train a series of lite VLMs on the synthetic dataset and experimental results demonstrate the effectiveness of the proposed scheme, where they achieve competitive performance on 17 benchmarks among 4B LVLMs, and even perform on par with 7B/13B-scale models on various benchmarks. This work highlights the feasibility of adopting high-quality data in crafting more efficient LVLMs. We name our dataset \textit{ALLaVA}, and open-source it to research community for developing better resource-efficient LVLMs for wider usage.

Related papers

• Transferring Textual Preferences to Vision-Language Understanding through Model Merging [65.41765072566287]
  This paper explores a training-free alternative by merging text-based reward models (RMs) with large vision-language models (LVLMs) Our approach shows that integrating these models leads to improved performance over LVLMs' scoring and text-based RMs.
  arXiv  Detail & Related papers  (2025-02-19T07:20:07Z)
• RLS3: RL-Based Synthetic Sample Selection to Enhance Spatial Reasoning in Vision-Language Models for Indoor Autonomous Perception [20.01853641155509]
  Vision-language model (VLM) fine-tuning for application-specific visual grounding based on natural language instructions has become one of the most popular approaches for learning-enabled autonomous systems. We propose a new generalizable framework to improve VLM fine-tuning by integrating it with a reinforcement learning (RL) agent.
  arXiv  Detail & Related papers  (2025-01-31T04:30:42Z)
• Multimodal Preference Data Synthetic Alignment with Reward Model [23.978820500281213]
  We propose a new framework in generating synthetic data using a reward model as a proxy of human preference for effective multimodal alignment with DPO training. Experiment results indicate that integrating selected synthetic data, such as from generative and rewards models can effectively reduce reliance on human-annotated data.
  arXiv  Detail & Related papers  (2024-12-23T09:29:40Z)
• NVLM: Open Frontier-Class Multimodal LLMs [64.00053046838225]
  We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks. We propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. We develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks.
  arXiv  Detail & Related papers  (2024-09-17T17:59:06Z)
• Concept-skill Transferability-based Data Selection for Large Vision-Language Models [56.0725292404808]
  We introduce COINCIDE, an effective and scalable data selection technique for training vision-language models. We cluster the training data using internal activations from a small model, which identifies concept-skill compositions needed by a target LVLM. Experiments demonstrate that COINCIDE achieves superior performance and data selection efficiency against 8 strong baselines.
  arXiv  Detail & Related papers  (2024-06-16T16:15:20Z)
• MoE-LLaVA: Mixture of Experts for Large Vision-Language Models [49.32669226551026]
  We propose a simple yet effective training strategy MoE-Tuning for LVLMs. MoE-LLaVA, a MoE-based sparse LVLM architecture, uniquely activates only the top-k experts through routers. Experiments show the significant performance of MoE-LLaVA in a variety of visual understanding and object hallucination benchmarks.
  arXiv  Detail & Related papers  (2024-01-29T08:13:40Z)
• Silkie: Preference Distillation for Large Visual Language Models [56.10697821410489]
  This paper explores preference distillation for large vision language models (LVLMs) We first build a vision-language feedback dataset utilizing AI annotation. We adopt GPT-4V to assess the generated outputs regarding helpfulness, visual faithfulness, and ethical considerations. The resulting model Silkie, achieves 6.9% and 9.5% relative improvement on the MME benchmark regarding the perception and cognition capabilities.
  arXiv  Detail & Related papers  (2023-12-17T09:44:27Z)

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.