Variational Bayesian Sequence-to-Sequence Networks for Memory-Efficient Sign Language Translation
Partaourides, Harris, Voskou, Andreas, Kosmopoulos, Dimitrios, Chatzis, Sotirios, Metaxas, Dimitris N.
Memory-efficient continuous Sign Language Translation is a significant challenge for the development of assisted technologies with real-time applicability for the deaf. In this work, we introduce a paradigm of designing recurrent deep networks whereby the output of the recurrent layer is derived from appropriate arguments from nonparametric statistics. A novel variational Bayesian sequence-to-sequence network architecture is proposed that consists of a) a full Gaussian posterior distribution for data-driven memory compression and b) a nonparametric Indian Buffet Process prior for regularization applied on the Gated Recurrent Unit non-gate weights. We dub our approach Stick-Breaking Recurrent network and show that it can achieve a substantial weight compression without diminishing modeling performance.
Feb-11-2021
- Country:
- Asia (0.04)
- North America > United States
- New Jersey (0.04)
- Europe
- Middle East > Cyprus
- Greece > West Greece
- Patra (0.04)
- Genre:
- Research Report (0.64)
- Industry:
- Education > Curriculum > Subject-Specific Education (0.63)
- Technology: