Minimizing prediction entropy during test time, by optimizing classifier and receptive-field scale parameters, improves semantic segmentation accuracy and robustness to scale shifts beyond one-step feedforward dynamic scale prediction.
End-to-end learning for structured prediction energy networks
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
-
Dynamic Scale Inference by Entropy Minimization
Minimizing prediction entropy during test time, by optimizing classifier and receptive-field scale parameters, improves semantic segmentation accuracy and robustness to scale shifts beyond one-step feedforward dynamic scale prediction.