Search

Your search keyword '"Yang, Boyu"' showing total 15 results
Start Over Author "Yang, Boyu" Publisher ieee
15 results on '"Yang, Boyu"'

14. Part-Based Semantic Transform for Few-Shot Semantic Segmentation.

Author

Yang, Boyu, Wan, Fang, Liu, Chang, Li, Bohao, Ji, Xiangyang, and Ye, Qixiang

Subjects
*SEMANTICS, *EXPECTATION-maximization algorithms, *IMAGE segmentation, *FEATURE extraction, *SHOT peening
Abstract

Few-shot semantic segmentation remains an open problem for the lack of an effective method to handle the semantic misalignment between objects. In this article, we propose part-based semantic transform (PST) and target at aligning object semantics in support images with those in query images by semantic decomposition-and-match. The semantic decomposition process is implemented with prototype mixture models (PMMs), which use an expectation–maximization (EM) algorithm to decompose object semantics into multiple prototypes corresponding to object parts. The semantic match between prototypes is performed with a min-cost flow module, which encourages correct correspondence while depressing mismatches between object parts. With semantic decomposition-and-match, PST enforces the network’s tolerance to objects’ appearance and/or pose variation and facilities channelwise and spatial semantic activation of objects in query images. Extensive experiments on Pascal VOC and MS-COCO datasets show that PST significantly improves upon state-of-the-arts. In particular, on MS-COCO, it improves the performance of five-shot semantic segmentation by up to 7.79% with a moderate cost of inference speed and model size. Code for PST is released at https://github.com/Yang-Bob/PST. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results