NexViTAD: Few-shot Unsupervised Cross-Domain Defect Detection via Vision Foundation Models and Multi-Task Learning

Documenti analoghi

• Vision-aware Multimodal Prompt Tuning for Uploadable Multi-source Few-shot Domain Adaptation
  di: Liu, Kuanghong, et al.
  Pubblicazione: (2025)
• CrackNex: a Few-shot Low-light Crack Segmentation Model Based on Retinex Theory for UAV Inspections
  di: Yao, Zhen, et al.
  Pubblicazione: (2024)
• VexNex
  di: VexNex
  Pubblicazione: (2026)
• Applying ViT in Generalized Few-shot Semantic Segmentation
  di: Geng, Liyuan, et al.
  Pubblicazione: (2024)
• DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning
  di: Duan, Yuxuan, et al.
  Pubblicazione: (2024)