MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation

Documenti analoghi

• Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively
  di: Yuan, Haobo, et al.
  Pubblicazione: (2024)
• DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection
  di: Xu, Shilin, et al.
  Pubblicazione: (2023)
• Explore In-Context Segmentation via Latent Diffusion Models
  di: Wang, Chaoyang, et al.
  Pubblicazione: (2024)
• CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
  di: Wu, Size, et al.
  Pubblicazione: (2023)
• EdgeSAM: Prompt-In-the-Loop Distillation for SAM
  di: Zhou, Chong, et al.
  Pubblicazione: (2023)