Text Descriptions are Compressive and Invariant Representations for Visual Learning.

Zhili Feng Anna Bair J. Zico Kolter

Published in: Trans. Mach. Learn. Res. (2024)

Keyphrases

visual learning
invariant representations
object recognition
invariant representation
integrating multiple
invariant properties
subspace learning
subject matter
d objects
data sets
image representation
recognizing objects
object detection
natural images
facial expression recognition