Unsupervised Transfer Learning for Spatiotemporal Predictive Networks
This addresses the challenge of enhancing spatiotemporal prediction models by leveraging diverse unsupervised sources, offering a novel transfer learning approach for domains like video analysis or weather forecasting, though it is incremental in building on existing transfer learning methods.
The paper tackles the problem of transferring knowledge from multiple unsupervisedly learned models to a new spatiotemporal prediction task, proposing a differentiable framework called transferable memory that improves performance on three benchmarks compared to finetuning.
This paper explores a new research problem of unsupervised transfer learning across multiple spatiotemporal prediction tasks. Unlike most existing transfer learning methods that focus on fixing the discrepancy between supervised tasks, we study how to transfer knowledge from a zoo of unsupervisedly learned models towards another predictive network. Our motivation is that models from different sources are expected to understand the complex spatiotemporal dynamics from different perspectives, thereby effectively supplementing the new task, even if the task has sufficient training samples. Technically, we propose a differentiable framework named transferable memory. It adaptively distills knowledge from a bank of memory states of multiple pretrained RNNs, and applies it to the target network via a novel recurrent structure called the Transferable Memory Unit (TMU). Compared with finetuning, our approach yields significant improvements on three benchmarks for spatiotemporal prediction, and benefits the target task even from less relevant pretext ones.