DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection

Documenti analoghi

• CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
  di: Wu, Size, et al.
  Pubblicazione: (2023)
• Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively
  di: Yuan, Haobo, et al.
  Pubblicazione: (2024)
• OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generation
  di: Wu, Size, et al.
  Pubblicazione: (2025)
• OMG-Seg: Is One Model Good Enough For All Segmentation?
  di: Li, Xiangtai, et al.
  Pubblicazione: (2024)
• F-LMM: Grounding Frozen Large Multimodal Models
  di: Wu, Size, et al.
  Pubblicazione: (2024)