Active Image Synthesis for Efficient Labeling
arXiv:1902.01522 · doi:10.1109/TPAMI.2020.2993221
Abstract
The great success achieved by deep neural networks attracts increasing attention from the manufacturing and healthcare communities. However, the limited availability of data and high costs of data collection are the major challenges for the applications in those fields. We propose in this work AISEL, an active image synthesis method for efficient labeling to improve the performance of the small-data learning tasks. Specifically, a complementary AISEL dataset is generated, with labels actively acquired via a physics-based method to incorporate underlining physical knowledge at hand. An important component of our AISEL method is the bidirectional generative invertible network (GIN), which can extract interpretable features from the training images and generate physically meaningful virtual images. Our AISEL method then efficiently samples virtual images not only further exploits the uncertain regions, but also explores the entire image space. We then discuss the interpretability of GIN both theoretically and experimentally, demonstrating clear visual improvements over the benchmarks. Finally, we demonstrate the effectiveness of our AISEL framework on aortic stenosis application, in which our method lower the labeling cost by while achieving a improvement in prediction accuracy.
References in corpus (23)
- A Survey on Deep Learning in Medical Image Analysis
- Auto-Encoding Variational Bayes
- Conditional Generative Adversarial Nets
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- How transferable are features in deep neural networks?
- The Effectiveness of Data Augmentation in Image Classification using Deep Learning
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Wide Residual Networks
- Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
- Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
- Generalizing from a Few Examples: A Survey on Few-Shot Learning
- Adversarial Feature Learning
- Adversarially Learned Inference
- Deep Bayesian Active Learning with Image Data
- Adversarial Active Learning for Deep Networks: a Margin Based Approach
- Generative Adversarial Active Learning
- Towards Deeper Understanding of Variational Autoencoding Models
- Generative Invertible Networks (GIN): Pathophysiology-Interpretable Feature Mapping and Virtual Patient Generation
- Projected support points: a new method for high-dimensional data reduction
- How Many Samples are Needed to Estimate a Convolutional or Recurrent Neural Network?
- Distance Measure Machines
- Adaptive design for Gaussian process regression under censoring