paper-with-me

홈 › Papers

AGLA: Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention

2024-06-18 · Wenbin An, Feng Tian, Sicong Leng, Jiahao Nie, Haonan Lin, Qianying Wang, Guang Dai, Ping Chen, Shijian Lu

Despite their great success across various multimodal tasks, Large Vision-Language Models (LVLMs) are facing a prevalent problem with object hallucinations, where the generated textual responses are inconsistent with ground-truth objects in the given image. This paper investigates various LVLMs and pinpoints attention deficiency toward discriminative local image features as one root cause of object hallucinations. Specifically, LVLMs predominantly attend to prompt-independent global image features, while failing to capture prompt-relevant local features, consequently undermining the visual grounding capacity of LVLMs and leading to hallucinations. To this end, we propose Assembly of Global and Local Attention (AGLA), a training-free and plug-and-play approach that mitigates object hallucinations by exploring an ensemble of global features for response generation and local features for visual discrimination simultaneously. Our approach exhibits an image-prompt matching scheme that captures prompt-relevant local features from images, leading to an augmented view of the input image where prompt-relevant content is reserved while irrelevant distractions are masked. With the augmented view, a calibrated decoding distribution can be derived by integrating generative global features from the original image and discriminative local features from the augmented image. Extensive experiments show that AGLA consistently mitigates object hallucinations and enhances general perception capability for LVLMs across various discriminative and generative benchmarks. Our code will be released at https://github.com/Lackel/AGLA.

📄 PDF Abstract BibTeX arXiv:2406.12718

Code (1)

lackel/agla 공식 구현 pytorch

Tasks

ObjectResponse GenerationVisual Grounding

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention

2025-01-01 · CVPR 2025 1 · Wenbin An, Feng Tian, Sicong Leng, Jiahao Nie 외

Despite great success across various multimodal tasks, Large Vision-Language Models (LVLMs) often encounter object hallucinations with generated textual responses being inconsistent with the actual objects in images.…

HallucinationResponse GenerationVisual Grounding

RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation

2024-08-21 · Xuanwang Zhang, Yunze Song, Yidong Wang, Shuyun Tang 외

Large Language Models (LLMs) demonstrate human-level capabilities in dialogue, reasoning, and knowledge retention. However, even the most advanced LLMs face challenges such as hallucinations and real-time updating of the…

RAGRetrievalRetrieval-augmented Generation

Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement

2026-05-12 · Zhenxin Qin, Qiang Li, Qingzhuo Wang, Ruiyang Qin 외 arxiv

Large Vision-Language Models (LVLMs) have achieved remarkable performance on diverse vision-language tasks. However, LVLMs still suffer from hallucinations, generating text that contradicts the visual input. Existing res…

Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding

2023-11-28 · CVPR 2024 1 · Sicong Leng, Hang Zhang, Guanzheng Chen, Xin Li 외

Large Vision-Language Models (LVLMs) have advanced considerably, intertwining visual recognition and language understanding to generate content that is not only coherent but also contextually attuned. Despite their succe…

HallucinationObjectObject Hallucination

Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance

2026-02-01 · Xinrong Chen, Xu Chu, Yingmin Qiu, Hengyuan Zhang 외 arxiv

Large Vision-Language Models (LVLMs) can reason from image-text inputs and perform well in various multimodal tasks. Despite this success, they are affected by language priors and often produce hallucinations. Hallucinat…

Visual Grounding