LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition.

Peng Xia Di Xu Lie Ju Ming Hu Jun Chen Zongyuan Ge

Published in: CoRR (2023)

Keyphrases

multi label
visual recognition
image classification
class specific
image representation
visual features
feature extraction
image features
visual words
bag of words
image annotation
multi modal
machine learning
decision trees
image segmentation
prior knowledge