Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition

Tianshui Chen
Tianshui Chen
Riquan Chen
Riquan Chen
Xiaolu Hui
Xiaolu Hui
Cited by: 0|Bibtex|Views24
Other Links: arxiv.org

Abstract:

Recognizing multiple labels of an image is a practical yet challenging task, and remarkable progress has been achieved by searching for semantic regions and exploiting label dependencies. However, current works utilize RNN/LSTM to implicitly capture sequential region/label dependencies, which cannot fully explore mutual interactions amo...More

Code:

Data:

Your rating :
0

 

Tags
Comments