I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification.

Muhammad Ferjad Naeem Yongqin Xian Luc Van Gool Federico Tombari

Published in: CoRR (2022)

Keyphrases

image classification
image representation
image features
multiscale
image data
single image
image analysis
learning process
document images
supervised learning
active learning
input image
image retrieval
edge detection
information retrieval systems
reinforcement learning
visual features
feature extraction
segmentation method
region of interest
test images
information retrieval
image collections
image content
feature points
low level
learning algorithm