SAM2RL: Towards Reinforcement Learning Memory Control in Segment Anything Model 2

Documenti analoghi

• Koo-Fu CLIP: Closed-Form Adaptation of Vision-Language Models via Fukunaga-Koontz Linear Discriminant Analysis
  di: Suchanek, Matej, et al.
  Pubblicazione: (2026)
• SAM 2: Segment Anything in Images and Videos
  di: Ravi, Nikhila, et al.
  Pubblicazione: (2024)
• AM-SAM: Automated Prompting and Mask Calibration for Segment Anything Model
  di: Li, Yuchen, et al.
  Pubblicazione: (2024)
• MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation
  di: Liao, Chenfei, et al.
  Pubblicazione: (2025)
• Single Image Test-Time Adaptation for Segmentation
  di: Janouskova, Klara, et al.
  Pubblicazione: (2023)