activity
20162023
most citedLarge-Scale Long-Tailed Recognition in an Open World

65 citations · 201 across the 25 of their papers we have counts for

collaborators
Showing 2021Show all

10 papers · 1 filter

cs.CV2021

Co-domain Symmetry for Complex-Valued Deep Learning

Utkarsh Singhal, Yifei Xing, Stella X. Yu

We study complex-valued scaling as a type of symmetry natural and unique to complex-valued measurements and representations. Deep Complex Networks (DCN) extends real-valued algebra…

cs.CV2021★ 15 cited

The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos

Runtao Liu, Zhirong Wu, Stella X. Yu +1

Humans can easily segment moving objects without knowing what they are. That objectness could emerge from continuous visual observations motivates us to model grouping and movement…

eess.IV2021★ 1 cited

High Fidelity Deep Learning-based MRI Reconstruction with Instance-wise Discriminative Feature Matching Loss

Ke Wang, Jonathan I Tamir, Alfredo De Goyeneche +4

Purpose: To improve reconstruction fidelity of fine structures and textures in deep learning (DL) based reconstructions. Methods: A novel patch-based Unsupervised Feature Loss (UFL…

cs.LG2021

Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifiers

Yunhui Guo, Xudong Wang, Yubei Chen +1

Hyperbolic space can naturally embed hierarchies, unlike Euclidean space. Hyperbolic Neural Networks (HNNs) exploit such representational power by lifting Euclidean features into h…

cs.CV2021

Compact and Optimal Deep Learning with Recurrent Parameter Generators

Jiayun Wang, Yubei Chen, Stella X. Yu +2

Deep learning has achieved tremendous success by training increasingly large models, which are then compressed for practical deployment. We propose a drastically different approach…

cs.SD2021★ 2 cited

Unsupervised Discriminative Learning of Sounds for Audio Event Classification

Sascha Hornauer, Ke Li, Stella X. Yu +2

Recent progress in network-based audio event classification has shown the benefit of pre-training models on visual data such as ImageNet. While this process allows knowledge transf…