InfoCLIP: Bridging Vision-Language Pretraining and Open-Vocabulary Semantic Segmentation via Information-Theoretic Alignment Transfer

Documenti analoghi

• InfoSAM: Fine-Tuning the Segment Anything Model from An Information-Theoretic Perspective
  di: Zhang, Yuanhong, et al.
  Pubblicazione: (2025)
• CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation
  di: Zhang, Dengke, et al.
  Pubblicazione: (2024)
• ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation
  di: Lan, Mengcheng, et al.
  Pubblicazione: (2024)
• MVGSR: Multi-View Consistent 3D Gaussian Super-Resolution via Epipolar Guidance
  di: Zhang, Kaizhe, et al.
  Pubblicazione: (2025)
• Mitigating Entangled Steering in Large Vision-Language Models for Hallucination Reduction
  di: Zhang, Yuanhong, et al.
  Pubblicazione: (2026)