CrevNet: Conditionally Reversible Video Prediction
arXiv:1910.11577
Abstract
Applying resolution-preserving blocks is a common practice to maximize information preservation in video prediction, yet their high memory consumption greatly limits their application scenarios. We propose CrevNet, a Conditionally Reversible Network that uses reversible architectures to build a bijective two-way autoencoder and its complementary recurrent predictor. Our model enjoys the theoretically guaranteed property of no information loss during the feature extraction, much lower memory consumption and computational efficiency.
References in corpus (5)
- Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
- NICE: Non-linear Independent Components Estimation
- Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
- PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning
- i-RevNet: Deep Invertible Networks
Cited by in corpus (4)
- Predicting Research Trends in Artificial Intelligence with Gradient Boosting Decision Trees and Time-aware Graph Neural Networks
- Learning to Transfer for Traffic Forecasting via Multi-task Learning
- Temporal Autoencoder with U-Net Style Skip-Connections for Frame Prediction
- From Single to Multiple: Leveraging Multi-level Prediction Spaces for Video Forecasting