Simulated+Unsupervised Learning With Adaptive Data Generation and Bidirectional Mappings


Nov 07, 2017 (modified: Nov 07, 2017) ICLR 2018 Conference Blind Submission readers: everyone Show Bibtex
  • Abstract: Collecting a large dataset with high quality annotations is expensive and time-consuming. Recently, Shrivastava et al. (2017) propose Simulated+Unsupervised (S+U) learning: It first learns a mapping from synthetic data to real data, translates a large amount of labeled synthetic data to the ones that resemble real data, and then trains a learning model on the translated data. While their algorithm is shown to achieve the state-of-the-art performance on the gaze estimation task, it may have a room for improvement, as it does not fully leverage flexibility of data simulation process and consider only the forward (synthetic to real) mapping. Inspired by these limitations, we propose a new S+U learning algorithm, which fully leverage the flexibility of data simulators and bidirectional mappings between synthetic data and real data. We show that our approach achieves the improved performance on the gaze estimation task, outperforming (Shrivastava et al., 2017).