Using k-means pseudo-labels from high-resolution features to train a two-layer transfer network improves low-resolution image classification mAP from 78.1 to 80.0 on VOC2007.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unsupervised Deep Feature Transfer for Low Resolution Image Classification
Using k-means pseudo-labels from high-resolution features to train a two-layer transfer network improves low-resolution image classification mAP from 78.1 to 80.0 on VOC2007.