no code implementations • 15 Aug 2024 • Chen Zeng, Jiahui Wang, Haoran Shen, Qiao Wang
For some types of functions, MLP outperforms or performs comparably to KAN.
no code implementations • 20 Jul 2024 • Haoran Shen, Chen Zeng, Jiahui Wang, Qiao Wang
noise with any fixed SNR, when we increase the amount of training data by a factor of $r$, the test-loss (RMSE) of KANs will exhibit a performance trend like $\text{test-loss} \sim \mathcal{O}(r^{-\frac{1}{2}})$ as $r\to +\infty$.
2 code implementations • 25 Dec 2023 • Jing Wang, Jinagyun Li, Chen Chen, Yisi Zhang, Haoran Shen, Tianxiang Zhang
In this paper, we propose a novel framework based on the adapter mechanism, namely Adaptive FSS, which can efficiently adapt the existing FSS model to the novel classes.
no code implementations • 21 Nov 2023 • Jiageng Zhong, Ming Li, Yinliang Chen, Zihang Wei, Fan Yang, Haoran Shen
For intelligent quadcopter UAVs, a robust and reliable autonomous planning system is crucial.
no code implementations • 28 Oct 2023 • Haoran Shen, Yifu Zhang, Wenxuan Wang, Chen Chen, Jing Liu, Shanshan Song, Jiangyun Li
As a pioneering work, a dynamic architecture network for medical volumetric segmentation (i. e. Med-DANet) has achieved a favorable accuracy and efficiency trade-off by dynamically selecting a suitable 2D candidate model from the pre-defined model bank for different slices.