Self-regularized prototypical network for few-shot semantic segmentation

• Published in: Pattern recognition 2023-01, Vol.133, p.109018, Article 109018
• Main Authors: Ding, Henghui, Zhang, Hui, Jiang, Xudong
• Format: Article
• Language: English
• Subjects: CNN; Few-shot segmentation; Iterative query inference; Non-parametric distance fidelity; Prototype; Prototypical network; Self-regularized; SRPNet
• ISSN: 0031-3203; 1873-5142
• DOI: 10.1016/j.patcog.2022.109018

•We propose a direct yet effective self-regularization module. Prototypes are generated, evaluated, and regularized under the supervision of support masks, which differs from existing works.•We adopt fidelity as the distance metric in prototype generation for the first time, which provides a more evident distinction for vectors.•We adopt an iterative query inference module, which uses a collection of prototypes for segmentation and improves the generalization ability for query inference.•We achieve new state-of-the-art performance on two few-shot segmentation benchmarks. 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 SRPNet achieves new state-of-art performance on 1-shot and 5-shot segmentation benchmarks.