Active Image Synthesis for Efficient Labeling
This work addresses data scarcity and labeling inefficiency for applications in fields like manufacturing and healthcare, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of limited data availability and high labeling costs in small-data learning tasks, such as in manufacturing and healthcare, by proposing AISEL, an active image synthesis method that reduces labeling costs by 90% and improves prediction accuracy by 15% in an aortic stenosis application.
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 $90\%$ while achieving a $15\%$ improvement in prediction accuracy.