Siming Yan
University of Texas at Austin
14 Papers
7 Citations
Siming Yan is an academic researcher from University of Texas at Austin. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 4, co-authored 10 publications. Previous affiliations of Siming Yan include Peking University & Cedars-Sinai Medical Center.
Chat about Author
Papers
Unsupervised neural network models of the ventral visual stream
Chengxu Zhuang,Siming Yan,Aran Nayebi,Martin Schrimpf,Michael C. Frank,James J. DiCarlo,Daniel L. K. Yamins +6 more
TL;DR: Recently, this article showed that neural network models learned with deep unsupervised contrastive embedding methods achieve neural prediction accuracy in multiple ventral visual cortical areas that equals or exceeds that of models derived using today's best supervised methods and that the mapping of neural network hidden layers is neuroanatomically consistent across the ventral stream.
253
Unsupervised Neural Network Models of the Ventral Visual Stream
Chengxu Zhuang,Siming Yan,Aran Nayebi,Martin Schrimpf,Michael C. Frank,James J. DiCarlo,Daniel L. K. Yamins +6 more
TL;DR: It is found that neural network models learned with deep unsupervised contrastive embedding methods achieve neural prediction accuracy in multiple ventral visual cortical areas that equals or exceeds that of models derived using today’s best supervised methods.
249
•Posted Content
HPNet: Deep Primitive Segmentation Using Hybrid Representations
TL;DR: HPNet as discussed by the authors leverages hybrid representations that combine one learned semantic descriptor, two spectral descriptors derived from predicted geometric parameters, as well as an adjacency matrix that encodes sharp edges.
26
•Posted Content
Scene Synthesis via Uncertainty-Driven Attribute Synchronization
Haitao Yang,Zaiwei Zhang,Siming Yan,Haibin Huang,Chongyang Ma,Yi Zheng,Chandrajit L. Bajaj,Qixing Huang +7 more
TL;DR: In this paper, the authors combine the strength of both neural network-based and conventional scene synthesis approaches to generate 3D scenes from training data, which provides uncertainties of object attributes and relative attributes.
15
3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining
TL;DR: In this article , the authors propose to ignore point position reconstruction and recover high-order features at masked points including surface normals and surface variations through a novel attention-based decoder which is independent of the encoder design.
8