Skip to main navigation Skip to search Skip to main content

Enhancing Spatial Consistency and Class-Level Diversity for Segmenting Fine-Grained Objects

  • Qi Zhao
  • , Binghao Liu
  • , Shuchang Lyu
  • , Chunlei Wang
  • , Yifan Yang*
  • *Corresponding author for this work
  • Beihang University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Semantic segmentation is a fundamental computer vision task attracting a lot of attention. However, limited works focus on semantic segmentation on fine-grained class scenario, which has more classes and greater inter-class similarity. Due to the lack of data available for this task, we establish two segmentation benchmarks, CUB-seg and FGSCR42-seg, based on CUB and FGSCR42 datasets. To solve the two major problems in this task, spatial inconsistency and extremely similar classes confusion, we propose the Spatial Consistency and Class-level Diversity enhancement Network. First, we build the Spatial Consistency Enhancement Module to take advantage of the low-frequency information in the feature, enhancing the spatial consistency. Second, Fine-grained Regions Contrastive Loss is designed to make the features of different classes more discriminative, promoting the class-level diversity. Extensive experiments show that our method can significantly improve the performance compared to baseline models. Visualization study also prove the effectiveness of our method for enhancing spatial consistency and class-level diversity.

Original languageEnglish
Title of host publicationNeural Information Processing - 30th International Conference, ICONIP 2023, Proceedings
EditorsBiao Luo, Long Cheng, Zheng-Guang Wu, Hongyi Li, Chaojie Li
PublisherSpringer Science and Business Media Deutschland GmbH
Pages292-304
Number of pages13
ISBN (Print)9789819981441
DOIs
StatePublished - 2024
Event30th International Conference on Neural Information Processing, ICONIP 2023 - Changsha, China
Duration: 20 Nov 202323 Nov 2023

Publication series

NameCommunications in Computer and Information Science
Volume1965 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference30th International Conference on Neural Information Processing, ICONIP 2023
Country/TerritoryChina
CityChangsha
Period20/11/2323/11/23

Keywords

  • Contrastive Learning
  • Fine-grained Semantic Segmentation
  • Spatial Consistency

Fingerprint

Dive into the research topics of 'Enhancing Spatial Consistency and Class-Level Diversity for Segmenting Fine-Grained Objects'. Together they form a unique fingerprint.

Cite this