Unsupervised EM-based joint optimization of interest point detector and descriptor via probability formulations of sparsity, repeatability and discriminability, yielding Property Network that outperforms SOTA on matching benchmarks without retraining.
Randomly insert some dark shapes into image
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Unsupervised Learning Framework of Interest Point Via Properties Optimization
Unsupervised EM-based joint optimization of interest point detector and descriptor via probability formulations of sparsity, repeatability and discriminability, yielding Property Network that outperforms SOTA on matching benchmarks without retraining.