Beyond General Prompts: Automated Prompt Refinement using Contrastive Class Alignment Scores for Disambiguating Objects in Vision-Language Models

Ähnliche Einträge

• Evaluating Cascaded Methods of Vision-Language Models for Zero-Shot Detection and Association of Hardhats for Increased Construction Safety
  von: Choi, Lucas, et al.
  Veröffentlicht: (2024)
• Evaluating Vision-Language Models for Zero-Shot Detection, Classification, and Association of Motorcycles, Passengers, and Helmets
  von: Choi, Lucas, et al.
  Veröffentlicht: (2024)
• Finding the Reflection Point: Unpadding Images to Remove Data Augmentation Artifacts in Large Open Source Image Datasets for Machine Learning
  von: Choi, Lucas, et al.
  Veröffentlicht: (2025)
• Near OOD Detection for Vision-Language Prompt Learning with Contrastive Logit Score
  von: Jung, Myong Chol, et al.
  Veröffentlicht: (2024)
• Technical Report for Argoverse2 Scenario Mining Challenges on Iterative Error Correction and Spatially-Aware Prompting
  von: Chen, Yifei, et al.
  Veröffentlicht: (2025)