The paper introduces unconstrained foreground object search, embedding backgrounds and objects in one similarity space and using a discriminator to generate noisy training triplets, achieving modestly higher retrieval precision than class-constrained baselines.
PatchMatch: A randomized correspon- dence algorithm for structural image editing
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
-
Unconstrained Foreground Object Search
The paper introduces unconstrained foreground object search, embedding backgrounds and objects in one similarity space and using a discriminator to generate noisy training triplets, achieving modestly higher retrieval precision than class-constrained baselines.