Generalized Additive Partial Linear Models (GAPLMs) are appealing for model interpretation and prediction. However, for GAPLMs, the covariates and the degree of smoothing in the nonparametric parts…
In this letter, we propose HV-Net, a new method for hypervolume approximation in evolutionary multiobjective optimization. The basic idea of HV-Net is to use DeepSets, a deep neural network with pe…
Temporal imaging provides a promising platform for ultrafast signal processing in both spectral and temporal domains. Most temporal imaging systems consist of time-lens and temporal dispersion; whi…
Point cloud instance segmentation has achieved huge progress with the emergence of deep learning. However, these methods are usually data-hungry with expensive and time-consuming dense point cloud …
Spatially-adaptive normalization (SPADE) is remarkably successful recently in conditional semantic image synthesis in T. Park et al. 2019 which modulates the normalized activation with spatially-va…
Despite the tremendous success, deep neural networks are exposed to serious IP infringement risks. Given a target deep model, if the attacker knows its full information, it can be easily stolen by …
Establishing correct correspondences between two images should consider both local and global spatial context. Given putative correspondences of feature points in two views, in this paper, we propo…
Ultrafast measurement ofbroadband radio frequency (RF) spectrum is of great importance in dispersion compensation, signal impairment monitoring and coherence analysis. As an all-optical RF spectrum…
Wafer failure pattern recognition can be used for root cause analysis, which is very important for yield learning. Recently, TestDNA was proposed to improve diagnosis resolution with data collected…
With the development of Internet of Things technology and artificial intelligence, the electric field sensor is required to be miniaturized, high performance, and low cost. At present, the commerci…