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.
gSLICr: SLIC superpixels at over 250Hz
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We introduce a parallel GPU implementation of the Simple Linear Iterative Clustering (SLIC) superpixel segmentation. Using a single graphic card, our implementation achieves speedups of up to $83\times$ from the standard sequential implementation. Our implementation is fully compatible with the standard sequential implementation and the software is now available online and is open source.
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.