Stella X. Yu

papers

1,190

total citations

papers (22)

Unsupervised Hierarchical Semantic Segmentation With Multiview Cosegmentation and Clustering Transformers

CVPR 2022arXiv

citations

Unsupervised Visual Attention and Invariance for Reinforcement Learning

CVPR 2021arXiv

citations

Unsupervised Selective Labeling for More Effective Semi-Supervised Learning

ECCV 2022arXiv

citations

CO-SNE: Dimensionality Reduction and Visualization for Hyperbolic Data

CVPR 2022arXiv

citations

Bootstrapping Objectness From Videos by Relaxed Common Fate and Visual Grouping

CVPR 2023arXiv

citations

Learning Hierarchical Image Segmentation For Recognition and By Recognition

ICLR 2024arXiv

citations

Co-Domain Symmetry for Complex-Valued Deep Learning

CVPR 2022arXiv

citations

Unsupervised Feature Learning with Emergent Data-Driven Prototypicality

CVPR 2024arXiv

citations

Let Humanoids Hike! Integrative Skill Development on Complex Trails

CVPR 2025arXiv

citations

Learning to Transform for Generalizable Instance-wise Invariance

ICCV 2023arXiv

citations

Open Ad-hoc Categorization with Contextualized Feature Learning

CVPR 2025arXiv

citations

Unsupervised Sketch to Photo Synthesis

ECCV 2020

citations

Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion

NEURIPS 2025arXiv

citations

ResoNet: Noise-Trained Physics-Informed MRI Off-Resonance Correction

NEURIPS 2023

citations

Normalize Filters! Classical Wisdom for Deep Vision

NEURIPS 2025arXiv

citations

Stella X. Yu

papers (22)

Cut and Learn for Unsupervised Object Detection and Instance Segmentation

Orthogonal Convolutional Neural Networks

Open Compound Domain Adaptation

Debiased Learning From Naturally Imbalanced Pseudo-Labels

Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination

Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifiers

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

Unsupervised Hierarchical Semantic Segmentation With Multiview Cosegmentation and Clustering Transformers

Unsupervised Visual Attention and Invariance for Reinforcement Learning

Unsupervised Selective Labeling for More Effective Semi-Supervised Learning

CO-SNE: Dimensionality Reduction and Visualization for Hyperbolic Data

Bootstrapping Objectness From Videos by Relaxed Common Fate and Visual Grouping

Learning Hierarchical Image Segmentation For Recognition and By Recognition

Co-Domain Symmetry for Complex-Valued Deep Learning

Unsupervised Feature Learning with Emergent Data-Driven Prototypicality

Let Humanoids Hike! Integrative Skill Development on Complex Trails

Learning to Transform for Generalizable Instance-wise Invariance

Open Ad-hoc Categorization with Contextualized Feature Learning

Unsupervised Sketch to Photo Synthesis

Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion

ResoNet: Noise-Trained Physics-Informed MRI Off-Resonance Correction

Normalize Filters! Classical Wisdom for Deep Vision

papers (22)

Cut and Learn for Unsupervised Object Detection and Instance Segmentation

Orthogonal Convolutional Neural Networks

Open Compound Domain Adaptation

Debiased Learning From Naturally Imbalanced Pseudo-Labels

Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination

Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifiers

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

Unsupervised Hierarchical Semantic Segmentation With Multiview Cosegmentation and Clustering Transformers

Unsupervised Visual Attention and Invariance for Reinforcement Learning

Unsupervised Selective Labeling for More Effective Semi-Supervised Learning

CO-SNE: Dimensionality Reduction and Visualization for Hyperbolic Data

Bootstrapping Objectness From Videos by Relaxed Common Fate and Visual Grouping

Learning Hierarchical Image Segmentation For Recognition and By Recognition

Co-Domain Symmetry for Complex-Valued Deep Learning

Unsupervised Feature Learning with Emergent Data-Driven Prototypicality

Let Humanoids Hike! Integrative Skill Development on Complex Trails

Learning to Transform for Generalizable Instance-wise Invariance

Open Ad-hoc Categorization with Contextualized Feature Learning

Unsupervised Sketch to Photo Synthesis

Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion

ResoNet: Noise-Trained Physics-Informed MRI Off-Resonance Correction

Normalize Filters! Classical Wisdom for Deep Vision