학술논문
Training Superpixel Network Only Once
Document Type
Periodical
Source
IEEE Signal Processing Letters IEEE Signal Process. Lett. Signal Processing Letters, IEEE. 31:1284-1288 2024
Subject
Language
ISSN
1070-9908
1558-2361
1558-2361
Abstract
Although existing deep superpixel methods have significantly improved the performance, they are generally dataset-specific and need re-training for unseen data. This issue results in the failure of deep superpixel methods when facing untrainable application scenarios. In this letter, we propose a novel deep superpixel algorithm to enhance the domain adaptability and generalization performance of deep superpixel methods. Specifically, we propose the domain-free embedding to replace traditional LAB color coding, reducing the network's reliance on training set statistical properties by narrowing the gap between training data and the real-world domain shift. Simultaneously, to prevent performance loss due to color information loss, we introduce the reconstructed contour constraint to directly enhance the boundary-fitting capability of superpixels. Experimental results demonstrate that our superpixel model achieve optimal cross-domain adaptation capability with just one training session, even facing extreme domain shift.