no code implementations • 16 Mar 2024 • Jiawei Li, Sitong Li, Shanshan Wang, Yicheng Zeng, Falong Tan, Chuanlong Xie
When trained using KNN on CIFAR10, MLOD-Fisher significantly lowers the false positive rate (FPR) from 24. 09% to 7. 47% on average compared to merely utilizing the features of the last layer.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • 15 Jan 2024 • Xuenan Peng, Chengqing Li, Yicheng Zeng, Chun-Lai Li
When combined with one SVS, four WMSs can lead to the formation of an eight-scroll or four-scroll attractor, while the integration of four WMSs and multiple SVSs can induce grid-multi-scroll attractors.
1 code implementation • 37th Conference on Neural Information Processing Systems (NeurIPS 2023) 2023 • Fangchen Yu, Runze Zhao, Zhan Shi, Yiwen Lu, Jicong Fan, Yicheng Zeng, Jianfeng Mao, Wenye Li
Secondly, we develop a series of affinity learning methods that equip the selfexpressive framework with ℓp-norm to construct an intrinsic affinity matrix with an adaptive extension.
2 code implementations • Thirty-Ninth Conference on Uncertainty in Artificial Intelligence (UAI) 2023 • Fangchen Yu, Yicheng Zeng, Jianfeng Mao, Wenye Li
To address this challenge, we propose matrix correction algorithms that leverage the positive semi-definiteness (PSD) of the similarity matrix to improve similarity estimation in both offline and online scenarios.
1 code implementation • 2 Feb 2023 • Xin Chen, Yicheng Zeng, Siyue Yang, Qiang Sun
We identify the optimal sketching size that minimizes out-of-sample prediction risks and demonstrate that the optimally sketched estimator exhibits stabler risk curves, eliminating the peaks of those for the full-sample estimator.