Respecting Modality Gap in Post-hoc Out-of-distribution Detection with Pre-trained Vision-Language Models

Documenti analoghi

• Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Models
  di: Peng, Bo, et al.
  Pubblicazione: (2026)
• Delving into Spectral Clustering with Vision-Language Representations
  di: Peng, Bo, et al.
  Pubblicazione: (2026)
• On the Learnability of Out-of-distribution Detection
  di: Fang, Zhen, et al.
  Pubblicazione: (2024)
• Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents
  di: Zhang, Zhizhen, et al.
  Pubblicazione: (2025)
• Post-hoc Probabilistic Vision-Language Models
  di: Baumann, Anton, et al.
  Pubblicazione: (2024)