Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage

• URL: http://arxiv.org/abs/2412.15484v2
• Date: Tue, 24 Dec 2024 04:42:49 GMT
• Title: Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage
• Authors: Saehyung Lee, Seunghyun Yoon, Trung Bui, Jing Shi, Sungroh Yoon,
• Abstract summary: Multimodal large language models (MLLMs) excel at generating highly detailed captions but often produce hallucinations. We propose a multiagent approach that leverages LLM-MLLM collaboration to correct given captions. Our proposed method significantly enhances the factual accuracy of captions, even improving those generated by GPT-4V.
• Score: 50.84150600032693
• License:
• Abstract: Multimodal large language models (MLLMs) excel at generating highly detailed captions but often produce hallucinations. Our analysis reveals that existing hallucination detection methods struggle with detailed captions. We attribute this to the increasing reliance of MLLMs on their generated text, rather than the input image, as the sequence length grows. To address this issue, we propose a multiagent approach that leverages LLM-MLLM collaboration to correct given captions. Additionally, we introduce an evaluation framework and a benchmark dataset to facilitate the systematic analysis of detailed captions. Our experiments demonstrate that our proposed evaluation method better aligns with human judgments of factuality than existing metrics and that existing approaches to improve the MLLM factuality may fall short in hyper-detailed image captioning tasks. In contrast, our proposed method significantly enhances the factual accuracy of captions, even improving those generated by GPT-4V. Finally, we highlight a limitation of VQA-centric benchmarking by demonstrating that an MLLM's performance on VQA benchmarks may not correlate with its ability to generate detailed image captions.

Related papers

• AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding [63.09928907734156]
  AlignVLM is a vision-text alignment method that maps visual features to a weighted average of text embeddings. Our experiments show that AlignVLM achieves state-of-the-art performance compared to prior alignment methods.
  arXiv  Detail & Related papers  (2025-02-03T13:34:51Z)
• Multi-LLM Collaborative Caption Generation in Scientific Documents [30.856381292477177]
  We introduce a framework called Multi-LLM Collaborative Figure Caption Generation (MLBCAP) Our approach unfolds in three key modules. Human evaluations demonstrate that informative captions produced by our approach rank better than human-written captions.
  arXiv  Detail & Related papers  (2025-01-05T14:09:12Z)
• Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysis [44.008094698200026]
  This paper investigates whether Multimodal LLMs can supplant traditional image captioning networks by evaluating their performance on various image description benchmarks. We explore both the zero-shot capabilities of these models and their adaptability to different semantic domains through fine-tuning methods. Our results demonstrate that while Multimodal LLMs achieve impressive zero-shot performance, fine-tuning for specific domains while maintaining their generalization capabilities intact remains challenging.
  arXiv  Detail & Related papers  (2024-12-04T19:01:06Z)
• Do More Details Always Introduce More Hallucinations in LVLM-based Image Captioning? [29.237078890377514]
  Large Vision-Language Models (LVLMs) excel in integrating visual and linguistic contexts to produce detailed content. Using LVLMs to generate descriptions often faces the challenge of object hallucination (OH), where the output text misrepresents actual objects in the input image. This paper proposes a novel decoding strategy, Differentiated Beam Decoding (DBD), along with a reliable new set of evaluation metrics.
  arXiv  Detail & Related papers  (2024-06-18T14:33:56Z)
• Benchmarking and Improving Detail Image Caption [12.078715675876674]
  Large vision-language model (LVLM) has long been regarded as a fundamental task in visual understanding. We propose to benchmark detail image caption task by curating high-quality evaluation datasets annotated by human experts. We also design a more reliable caption evaluation metric called CAPTURE.
  arXiv  Detail & Related papers  (2024-05-29T13:54:12Z)
• Browse and Concentrate: Comprehending Multimodal Content via prior-LLM Context Fusion [70.9767518332692]
  Multimodal Large Language Models (MLLMs) that incorporate LLMs with pre-trained vision models have recently demonstrated impressive performance across diverse vision-language tasks. However, they fall short to comprehend context involving multiple images. We propose a two phase paradigm, browse-and-concentrate, to enable in-depth multimodal context fusion.
  arXiv  Detail & Related papers  (2024-02-19T14:59:07Z)
• Q-Bench+: A Benchmark for Multi-modal Foundation Models on Low-level Vision from Single Images to Pairs [71.07108539262721]
  We design benchmark settings to emulate human language responses related to low-level vision. We extend the low-level perception-related question-answering and description evaluations of MLLMs from single images to image pairs. We demonstrate that several MLLMs have decent low-level visual competencies on single images, but only GPT-4V exhibits higher accuracy on pairwise comparisons than humans.
  arXiv  Detail & Related papers  (2024-02-11T06:44:11Z)
• Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences [80.54979242912944]
  This paper introduces Mementos, a new benchmark designed to assess MLLMs' sequential image reasoning abilities. We find that MLLMs struggle to accurately describe dynamic information about given image sequences, often leading to hallucinations/misrepresentations of objects.
  arXiv  Detail & Related papers  (2024-01-19T07:10:13Z)
• Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions [126.3136109870403]
  We introduce a generic and lightweight Visual Prompt Generator Complete module (VPG-C) VPG-C infers and completes the missing details essential for comprehending demonstrative instructions. We build DEMON, a comprehensive benchmark for demonstrative instruction understanding.
  arXiv  Detail & Related papers  (2023-08-08T09:32:43Z)

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.