DouC: Dual-Branch CLIP for Training-Free Open-Vocabulary Segmentation

Documenti analoghi

• Delta-LLaVA: Base-then-Specialize Alignment for Token-Efficient Vision-Language Models
  di: Zamini, Mohamad, et al.
  Pubblicazione: (2025)
• Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation
  di: Bai, Sule, et al.
  Pubblicazione: (2024)
• Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation
  di: Shao, Tong, et al.
  Pubblicazione: (2024)
• Improving Visual Discriminability of CLIP for Training-Free Open-Vocabulary Semantic Segmentation
  di: Zhou, Jinxin, et al.
  Pubblicazione: (2025)
• A Training-Free Framework for Open-Vocabulary Image Segmentation and Recognition with EfficientNet and CLIP
  di: Dai, Ying, et al.
  Pubblicazione: (2025)