TY - GEN
T1 - Dichotomous Image Segmentation with Frequency Priors
AU - Zhou, Yan
AU - Dong, Bo
AU - Wu, Yuanfeng
AU - Zhu, Wentao
AU - Chen, Geng
AU - Zhang, Yanning
N1 - Publisher Copyright:
© 2023 International Joint Conferences on Artificial Intelligence. All rights reserved.
PY - 2023
Y1 - 2023
N2 - Dichotomous image segmentation (DIS) has a wide range of real-world applications and gained increasing research attention in recent years. In this paper, we propose to tackle DIS with informative frequency priors. Our model, called FP-DIS, stems from the fact that prior knowledge in the frequency domain can provide valuable cues to identify fine-grained object boundaries. Specifically, we propose a frequency prior generator to jointly utilize a fixed filter and learnable filters to extract informative frequency priors. Before embedding the frequency priors into the network, we first harmonize the multi-scale side-out features to reduce their heterogeneity. This is achieved by our feature harmonization module, which is based on a gating mechanism to harmonize the grouped features. Finally, we propose a frequency prior embedding module to embed the frequency priors into multi-scale features through an adaptive modulation strategy. Extensive experiments on the benchmark dataset, DIS5K, demonstrate that our FP-DIS outperforms state-of-the-art methods by a large margin in terms of key evaluation metrics.
AB - Dichotomous image segmentation (DIS) has a wide range of real-world applications and gained increasing research attention in recent years. In this paper, we propose to tackle DIS with informative frequency priors. Our model, called FP-DIS, stems from the fact that prior knowledge in the frequency domain can provide valuable cues to identify fine-grained object boundaries. Specifically, we propose a frequency prior generator to jointly utilize a fixed filter and learnable filters to extract informative frequency priors. Before embedding the frequency priors into the network, we first harmonize the multi-scale side-out features to reduce their heterogeneity. This is achieved by our feature harmonization module, which is based on a gating mechanism to harmonize the grouped features. Finally, we propose a frequency prior embedding module to embed the frequency priors into multi-scale features through an adaptive modulation strategy. Extensive experiments on the benchmark dataset, DIS5K, demonstrate that our FP-DIS outperforms state-of-the-art methods by a large margin in terms of key evaluation metrics.
UR - http://www.scopus.com/inward/record.url?scp=85170360684&partnerID=8YFLogxK
U2 - 10.24963/ijcai.2023/202
DO - 10.24963/ijcai.2023/202
M3 - 会议稿件
AN - SCOPUS:85170360684
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 1822
EP - 1830
BT - Proceedings of the 32nd International Joint Conference on Artificial Intelligence, IJCAI 2023
A2 - Elkind, Edith
PB - International Joint Conferences on Artificial Intelligence
T2 - 32nd International Joint Conference on Artificial Intelligence, IJCAI 2023
Y2 - 19 August 2023 through 25 August 2023
ER -