On December 9, 2023, The Thirty-Eighth AAAI Conference on Artistic Intelligence (AAAI-24) announced the admission results, and a paper by Professor Zhu Haijiang's research group was accepted. The first author of this paper is Liu Yutong, a Ph.D. student in the School of Information Science and Technology, and the corresponding author is Professor Zhu Haijiang. Beijing University of Chemical Technology (BUCT) is the only completing institution.
Paper Information: Yutong Liu, Haijiang Zhu, Mengting Liu, Huaiyuan Yu, Zihan Chen, Jie Gao: “Rolling-Unet: Revitalizing MLP’s Ability to Efficiently Extract Long-Distance Dependencies for Medical Image Segmentation”. The Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24)
To address the limitations of CNNs in capturing long-range dependencies and Transformers in computational complexity and local feature learning, this paper proposes an efficient R-MLP module that extracts image remote dependencies, and a Lo2 block that can encode both local context and long-range relations of images without introducing excessive computational overhead. Experimental results on four public datasets with different characteristics demonstrate that our method achieves superior performance compared to the state-of-the-art methods.
Figure 1. The overview of the proposed Rolling-Unet.
The Association for the Advancement of Artificial Intelligence (AAAI) is one of the major international academic organizations in the field of artificial intelligence. The AAAI Conference on Artificial Intelligence, hosted by the association, is one of the top international academic conferences on artificial intelligence. The AAAI Conference is held once a year and belongs to the Class A Conference of the China Computer Federation in the Field of Artificial Intelligence (CCF A) and the Class A Conference of the Chinese Association of Automation (CAA A). In the academic journal conference influence ranking released by Google Scholar in July 2023, AAAI ranked 14th among journals/conferences in the field of "Engineering and Computer Science".