.png){kind=icon}
.png){kind=icon}
Return
Negative-Sampling prompt learning for hard negative sample discrimination
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2026.115603.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Verifies the feasibility of using prompt learner as a negative sampler for vision-language models. • Proposes an efficient negative sampling framework, ensuring similarity and reliability. • Devises a plug-and-play module to enhance cross-modal fusion on small-scale datasets.
Keywords:
prompt learning
negative sampling
vision-language models
cross-modal fusion
hard negative discrimination