Mitigating Low-Level Visual Hallucinations Requires Self-Awareness: Database, Model and Training Strategy

The rapid development of multimodal large language models has resulted in remarkable advancements in visual perception and understanding, consolidating several tasks into a single visual question-answering framework. However, these models are prone to hallucinations, which limit their reliability as...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on circuits and systems for video technology s. 1
Hlavní autoři: Sun, Yinan, Min, Xiongkuo, Zhang, Zicheng, Gao, Yixuan, Cao, Yuqin, Zhai, Guangtao
Médium: Journal Article
Jazyk:angličtina
Vydáno: IEEE 2025
Témata:
Accuracy
Analytical models
Feature extraction
hallucination
Image quality
image quality assessment
Large language models
low-level vision
Multimodal large language models
Reliability
Training
Visual databases
Visual perception
Visualization
ISSN:1051-8215, 1558-2205
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The rapid development of multimodal large language models has resulted in remarkable advancements in visual perception and understanding, consolidating several tasks into a single visual question-answering framework. However, these models are prone to hallucinations, which limit their reliability as artificial intelligence systems. While this issue is extensively researched in natural language processing and image captioning, there remains a lack of investigation of hallucinations in Low-level Visual Perception and Understanding (HLPU), especially in the context of image quality assessment tasks. We consider that these hallucinations arise from an absence of clear self-awareness within the models. To address this issue, we first introduce the HLPU instruction database, the first instruction database specifically focused on hallucinations in low-level vision tasks. This database contains approximately 200K question-answer pairs and comprises four subsets, each covering different types of instructions. Subsequently, we propose the Self-Awareness Failure Elimination (SAFEQA) model, which utilizes image features, salient region features and quality features to improve the perception and comprehension abilities of the model in low-level vision tasks. Furthermore, we propose the Enhancing Self-Awareness Preference Optimization (ESA-PO) framework to increase the model's awareness of knowledge boundaries, thereby mitigating the incidence of hallucination. Finally, we conduct comprehensive experiments on low-level vision tasks, with the results demonstrating that our proposed method significantly enhances self-awareness of the model in these tasks and reduces hallucinations. Notably, our proposed method improves both accuracy and self-awareness of the proposed model and outperforms close-source models in terms of various evaluation metrics. This research contributes to the advancement of self-awareness capabilities in multimodal large language models, particularly for low-level visual perception and understanding tasks.
ISSN:1051-8215
1558-2205
DOI:10.1109/TCSVT.2025.3619558