FaNe: Towards Fine-Grained Cross-Modal Contrast with False-Negative Reduction and Text-Conditioned Sparse Attention

Documenti analoghi

• Semi-Supervised Dual-Threshold Contrastive Learning for Ultrasound Image Classification and Segmentation
  di: Zhang, Peng, et al.
  Pubblicazione: (2025)
• Prototype Contrastive Consistency Learning for Semi-Supervised Medical Image Segmentation
  di: He, Shihuan, et al.
  Pubblicazione: (2025)
• OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs
  di: Chen, Feng, et al.
  Pubblicazione: (2025)
• FALCON: False-Negative Aware Learning of Contrastive Negatives in Vision-Language Alignment
  di: Kim, Myunsoo, et al.
  Pubblicazione: (2025)
• False Negative Reduction in Video Instance Segmentation using Uncertainty Estimates
  di: Maag, Kira
  Pubblicazione: (2021)