A capsule network operating on superpixel-pooled VGG-16 features can classify images with about 89% accuracy on a small four-class dataset and provides part-whole explanations without segmentation labels.
Understanding convolution for semantic segmentation
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
-
Recognizing Image Objects by Relational Analysis Using Heterogeneous Superpixels and Deep Convolutional Features
A capsule network operating on superpixel-pooled VGG-16 features can classify images with about 89% accuracy on a small four-class dataset and provides part-whole explanations without segmentation labels.