signADAM and signADAM++ are new first-order optimizers that incorporate sign operations and a confidence-based sparsity mechanism, with claimed empirical superiority and theoretical convergence over ADAM and sign-based baselines.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2019 2verdicts
UNVERDICTED 2representative citing papers
A framework learns collection embeddings from runway images and applies RNN/LSTM to predict next-season designs at 78.42% average AUC over 32 years of data.
citing papers explorer
-
signADAM: Learning Confidences for Deep Neural Networks
signADAM and signADAM++ are new first-order optimizers that incorporate sign operations and a confidence-based sparsity mechanism, with claimed empirical superiority and theoretical convergence over ADAM and sign-based baselines.
-
Predicting Next-Season Designs on High Fashion Runway
A framework learns collection embeddings from runway images and applies RNN/LSTM to predict next-season designs at 78.42% average AUC over 32 years of data.