J
Jiamian Wang
Researcher at University of Southern California
Publications - 6
Citations - 70
Jiamian Wang is an academic researcher from University of Southern California. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 1, co-authored 1 publications receiving 28 citations.
Papers
More filters
Journal ArticleDOI
Outlier exposure with confidence control for out-of-distribution detection
TL;DR: A novel loss function is proposed that gives rise to a novel method, Outlier Exposure with Confidence Control (OECC), which achieves superior results in out-of-distribution detection with OE both on image and text classification tasks without requiring access to OOD samples.
Journal ArticleDOI
S^2-Transformer for Mask-Aware Hyperspectral Image Reconstruction
TL;DR: Wang et al. as mentioned in this paper proposed a spatial-spectral (S^2-) Transformer network with a mask-aware learning strategy, which simultaneously leveraged spatial and spectral attention modeling to disentangle the blended information in the 2D measurement along both two dimensions.
Proceedings ArticleDOI
Calibrate Automated Graph Neural Network via Hyperparameter Uncertainty
TL;DR: A hyperparameter uncertainty-induced graph convolutional network (HyperU-GCN) with a bilevel formulation, where the upper-level problem explicitly reasons uncertainties by developing a probabilistic hypernetworks through a variational Bayesian lens, which could achieve calibrated predictions in a similar way to Bayesian model averaging over hyperparameters.
Modeling Mask Uncertainty in Hyperspectral Image Reconstruction (Supplementary Material)
TL;DR: In this article , an alternating reconstruction backbone network (SRN) was proposed for spectral fidelity analysis and self-tuning variance analysis, and the spectral fidelity of the reconstruction results was evaluated.
Journal ArticleDOI
Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution
TL;DR: Zhang et al. as discussed by the authors proposed an iterative soft shrinkage-percentage (ISS-P) method by optimizing the sparse structure of a randomly initialized network at each iteration and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.