1 code implementation • 28 Mar 2024 • Benhao Huang
These methods are crucial for assessing the quality of images relative to their textual descriptions, and they must accurately mirror human perception.
no code implementations • 3 Feb 2024 • Lu Chen, Shaofeng Li, Benhao Huang, Fan Yang, Zheng Li, Jie Li, Yuan Luo
However, in this work, we reveal the existence of a harmless perturbation space, in which perturbations drawn from this space, regardless of their magnitudes, leave the network output unchanged when applied to inputs.
1 code implementation • 29 Jan 2024 • Lu Chen, Siyu Lou, Benhao Huang, Quanshi Zhang
Faithfully summarizing the knowledge encoded by a deep neural network (DNN) into a few symbolic primitive patterns without losing much information represents a core challenge in explainable AI.