TY - GEN
T1 - Enhancing Spatial Consistency and Class-Level Diversity for Segmenting Fine-Grained Objects
AU - Zhao, Qi
AU - Liu, Binghao
AU - Lyu, Shuchang
AU - Wang, Chunlei
AU - Yang, Yifan
N1 - Publisher Copyright:
© 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
KW - Contrastive Learning
KW - Fine-grained Semantic Segmentation
KW - Spatial Consistency
UR - https://www.scopus.com/pages/publications/85178570100
U2 - 10.1007/978-981-99-8145-8_23
DO - 10.1007/978-981-99-8145-8_23
M3 - 会议稿件
AN - SCOPUS:85178570100
SN - 9789819981441
T3 - Communications in Computer and Information Science
SP - 292
EP - 304
BT - Neural Information Processing - 30th International Conference, ICONIP 2023, Proceedings
A2 - Luo, Biao
A2 - Cheng, Long
A2 - Wu, Zheng-Guang
A2 - Li, Hongyi
A2 - Li, Chaojie
PB - Springer Science and Business Media Deutschland GmbH
T2 - 30th International Conference on Neural Information Processing, ICONIP 2023
Y2 - 20 November 2023 through 23 November 2023
ER -