Self-Regularized Prototypical Network for Few-Shot Semantic Segmentation

Abstract

The deep CNNs in image semantic segmentation typically require a large number of densely-annotated images for training and have difficulties in generalizing to unseen object categories. Therefore, few-shot segmentation has been developed to perform segmentation with just a few annotated examples. In this work, we tackle the few-shot segmentation using a self-regularized prototypical network (SRPNet) based on prototype extraction for better utilization of the support information. The proposed SRPNet extracts class-specific prototype representations from support images and generates segmentation masks for query images by a distance metric -the fidelity. A direct yet effective prototype regularization on support set is proposed in SRPNet, in which the generated prototypes are evaluated and regularized on the support set itself. The extent to which the generated prototypes restore the support mask imposes an upper limit on performance. The performance on the query set should never exceed the upper limit no matter how complete the knowledge is generalized from support set to query set. With the specific prototype regularization, SRPNet fully exploits knowledge from the support and offers high-quality prototypes that are representative for each semantic class and meanwhile discriminative for different classes. The query performance is further improved by an iterative query inference (IQI) module that combines a set of regularized prototypes. Our proposed

Using optical coherence tomography to assess luster of pearls: technique suitability and insights

“…We also tried to use some new methods for small sample clarification. With very little supervision from labeled data, few-shot learning was one of the typical ones 28 . In the original, the few-shot classifier could recognize new categories from very few labeled examples, while a few examples trained classifiers in each class, and the tanning procedure was decomposed into the meta-learning phases where transferable knowledge was learned based on different strategies.…”