Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910973599678464 |
|---|---|
| author | Lee, Jihoon Song, Min |
| author_facet | Lee, Jihoon Song, Min |
| contents | Despite significant advancements in Large Vision-Language Models, Object Hallucination (OH) remains a persistent challenge. Building upon prior studies on contrastive decoding that address this issue without requiring additional model training, we introduce RVCD (Retrieval Visual Contrastive Decoding), an advanced method to suppress OH. RVCD leverages both negative and positive images at the logit level, explicitly referencing AI-generated images designed to represent a single concept. Our approach demonstrates substantial improvements over existing decoding-based methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_20569 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Models Lee, Jihoon Song, Min Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Despite significant advancements in Large Vision-Language Models, Object Hallucination (OH) remains a persistent challenge. Building upon prior studies on contrastive decoding that address this issue without requiring additional model training, we introduce RVCD (Retrieval Visual Contrastive Decoding), an advanced method to suppress OH. RVCD leverages both negative and positive images at the logit level, explicitly referencing AI-generated images designed to represent a single concept. Our approach demonstrates substantial improvements over existing decoding-based methods. |
| title | Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2505.20569 |