Do More Details Always Introduce More Hallucinations in LVLM-based Image Captioning?

• URL: http://arxiv.org/abs/2406.12663v1
• Date: Tue, 18 Jun 2024 14:33:56 GMT
• Title: Do More Details Always Introduce More Hallucinations in LVLM-based Image Captioning?
• Authors: Mingqian Feng, Yunlong Tang, Zeliang Zhang, Chenliang Xu,
• Abstract summary: 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.
• Score: 29.237078890377514
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Vision-Language Models (LVLMs) excel in integrating visual and linguistic contexts to produce detailed content, facilitating applications such as image captioning. However, using LVLMs to generate descriptions often faces the challenge of object hallucination (OH), where the output text misrepresents actual objects in the input image. While previous studies attribute the occurrence of OH to the inclusion of more details, our study finds technical flaws in existing metrics, leading to unreliable evaluations of models and conclusions about OH. This has sparked a debate on the question: Do more details always introduce more hallucinations in LVLM-based image captioning? In this paper, we address this debate by proposing a novel decoding strategy, Differentiated Beam Decoding (DBD), along with a reliable new set of evaluation metrics: CLIP-Precision, CLIP-Recall, and CLIP-F1. DBD decodes the wealth of information hidden in visual input into distinct language representations called unit facts in parallel. This decoding is achieved via a well-designed differential score that guides the parallel search and candidate screening. The selected unit facts are then aggregated to generate the final caption. Our proposed metrics evaluate the comprehensiveness and accuracy of image captions by comparing the embedding groups of ground-truth image regions and generated text partitions. Extensive experiments on the Visual Genome dataset validate the effectiveness of our approach, demonstrating that it produces detailed descriptions while maintaining low hallucination levels.

Related papers

• Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance [67.26434607115392]
  Large vision-language models (LVLMs) have achieved impressive results in various vision-language tasks. LVLMs suffer from hallucinations caused by language bias, leading to diminished focus on images and ineffective visual comprehension. We propose LACING to address the language bias of LVLMs with muLtimodal duAl-attention meChanIsm (MDA) aNd soft-image Guidance (IFG)
  arXiv  Detail & Related papers  (2024-11-21T16:33:30Z)
• Bridging the Visual Gap: Fine-Tuning Multimodal Models with Knowledge-Adapted Captions [31.637204677787576]
  We introduce Knowledge Adapted (KnowAda) fine-tuning, a data-centric approach that automatically adapts training data with the model's existing knowledge and visual understanding. KnowAda minimizes hallucinations while preserving high descriptiveness. Our results show that KnowAda outperforms various baselines in both automatic metrics and human evaluations.
  arXiv  Detail & Related papers  (2024-11-13T20:50:04Z)
• Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding [14.701135083174918]
  Large Vision-Language Models (LVLMs) generate detailed and coherent responses from visual inputs. They are prone to generate hallucinations due to an over-reliance on language priors. We propose a novel method, Summary-Guided Decoding (SGD)
  arXiv  Detail & Related papers  (2024-10-17T08:24:27Z)
• Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding [36.81476620057058]
  Large Vision-Language Models (LVLMs) are susceptible to object hallucinations. Current approaches often rely on the model's token likelihoods or other internal information. We introduce our CLIP-Guided Decoding approach to reduce object hallucination at decoding time.
  arXiv  Detail & Related papers  (2024-02-23T12:57:16Z)
• Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models [121.83413400686139]
  This paper proposes to improve the visual perception ability of MLLMs through a mixture-of-experts knowledge enhancement mechanism. We introduce a novel method that incorporates multi-task encoders and visual tools into the existing MLLMs training and inference pipeline.
  arXiv  Detail & Related papers  (2024-01-06T02:02:34Z)
• Good Questions Help Zero-Shot Image Reasoning [110.1671684828904]
  Question-Driven Visual Exploration (QVix) is a novel prompting strategy that enhances the exploratory capabilities of large vision-language models (LVLMs) QVix enables a wider exploration of visual scenes, improving the LVLMs' reasoning accuracy and depth in tasks such as visual question answering and visual entailment. Our evaluations on various challenging zero-shot vision-language benchmarks, including ScienceQA and fine-grained visual classification, demonstrate that QVix significantly outperforms existing methods.
  arXiv  Detail & Related papers  (2023-12-04T03:18:51Z)
• Mitigating Hallucination in Visual Language Models with Visual Supervision [33.05550629039951]
  Large vision-language models (LVLMs) suffer from hallucination a lot. Key problem lies in its weak ability to comprehend detailed content in a multi-modal context. In this paper, we bring more detailed vision annotations and more discriminative vision models to facilitate the training of LVLMs.
  arXiv  Detail & Related papers  (2023-11-27T09:30:02Z)
• Resolving References in Visually-Grounded Dialogue via Text Generation [3.8673630752805446]
  Vision-language models (VLMs) have shown to be effective at image retrieval based on simple text queries, but text-image retrieval based on conversational input remains a challenge. We propose fine-tuning a causal large language model (LLM) to generate definite descriptions that summarize coreferential information found in the linguistic context of references. We then use a pretrained VLM to identify referents based on the generated descriptions, zero-shot.
  arXiv  Detail & Related papers  (2023-09-23T17:07:54Z)
• Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination [88.74459704391214]
  In this work, we investigate a more realistic unsupervised multimodal machine translation (UMMT) setup. We represent the input images and texts with the visual and language scene graphs (SG), where such fine-grained vision-language features ensure a holistic understanding of the semantics. Several SG-pivoting based learning objectives are introduced for unsupervised translation training. Our method outperforms the best-performing baseline by significant BLEU scores on the task and setup.
  arXiv  Detail & Related papers  (2023-05-20T18:17:20Z)
• Prompt-based Learning for Unpaired Image Captioning [86.44188293709307]
  Unpaired Image Captioning (UIC) has been developed to learn image descriptions from unaligned vision-language sample pairs. Recent successes of Vision-Language Pre-Trained Models (VL-PTMs) have triggered the development of prompt-based learning. We present in this paper a novel scheme based on prompt to train the UIC model, making best use of the powerful generalization ability.
  arXiv  Detail & Related papers  (2022-05-26T03:13:43Z)
• Fine-grained Image Captioning with CLIP Reward [104.71533106301598]
  We propose using CLIP, a multimodal encoder trained on huge image-text pairs from web, to calculate multimodal similarity and use it as a reward function. We also propose a simple finetuning strategy of the CLIP text encoder to improve grammar that does not require extra text annotation. In experiments on text-to-image retrieval and FineCapEval, the proposed CLIP-guided model generates more distinctive captions than the CIDEr-optimized model.
  arXiv  Detail & Related papers  (2022-05-26T02:46:09Z)

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.