Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding

Documenti analoghi

• HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
  di: Chen, Zhaorun, et al.
  Pubblicazione: (2024)
• RankCLIP: Ranking-Consistent Language-Image Pretraining
  di: Zhang, Yiming, et al.
  Pubblicazione: (2024)
• Dropout Prompt Learning: Towards Robust and Adaptive Vision-Language Models
  di: Chen, Biao, et al.
  Pubblicazione: (2025)
• Enhancing Monte Carlo Dropout Performance for Uncertainty Quantification
  di: Asgharnezhad, Hamzeh, et al.
  Pubblicazione: (2025)
• Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding
  di: Deng, Ailin, et al.
  Pubblicazione: (2024)