Can I read Dual Prototypical Contrastive Learning for Few-shot Semantic Segmentation on EtoBox?

Dual Prototypical Contrastive Learning for Few-shot Semantic Segmentation by Kwon, Hyeongjun; Jeong, Somi; Kim, Sunok; Sohn, Kwanghoon is a scholarly article available to read on EtoBox.

What is Dual Prototypical Contrastive Learning for Few-shot Semantic Segmentation about?

We address the problem of few-shot semantic segmentation (FSS), which aims to segment novel class objects in a target image with a few annotated samples. Though recent advances have been made by incorporating prototype-based metric learning, existing methods still show limited performance under extreme intra-class object variations and semantically similar inter-class objects due to their poor feature representation. To tackle this problem, we propose a dual prototypical contrastive learning approach tailored to the FSS task to capture the representative semanticfeatures effectively. The main idea is to encourage the prototypes more discriminative by increasing inter-class distance while reducing intra-class distance in prototype feature space. To this end, we first present a class-specific contrastive loss with a dynamic prototype dictionary that stores the class-aware prototypes during training, thus enabling the same class prototypes similar and the different class prototypes to be dissimilar. Furthermore, we introduce a class-agnostic contrastive loss to enhance the generalization ability to unseen classes by compressing the feature distribution of semantic class within each ep

Author

Kwon, Hyeongjun; Jeong, Somi; Kim, Sunok; Sohn, Kwanghoon

Published

2021

Language

EN