Stella X. Yu

35

Papers

20

Total Citations

Papers (35)

Learning Hierarchical Image Segmentation For Recognition and By Recognition

Let Humanoids Hike! Integrative Skill Development on Complex Trails

Normalize Filters! Classical Wisdom for Deep Vision

Unsupervised Feature Learning with Emergent Data-Driven Prototypicality

FlowWeb: Joint Image Set Alignment by Weaving Consistent, Pixel-Wise Correspondences

Learning Lightness From Human Judgement on Relative Reflectance

Affinity CNN: Learning Pixel-Centric Pairwise Relations for Figure/Ground Embedding

Convolutional Random Walk Networks for Semantic Image Segmentation

Learning Non-Lambertian Object Intrinsics Across ShapeNet Categories

Multigrid Neural Architectures

Unsupervised Feature Learning via Non-Parametric Instance Discrimination

Large-Scale Long-Tailed Recognition in an Open World

Adversarial Structure Matching for Structured Prediction Tasks

Orthogonal Convolutional Neural Networks

Open Compound Domain Adaptation

Unsupervised Visual Attention and Invariance for Reinforcement Learning

Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination

Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifiers

Debiased Learning From Naturally Imbalanced Pseudo-Labels

CO-SNE: Dimensionality Reduction and Visualization for Hyperbolic Data

Co-Domain Symmetry for Complex-Valued Deep Learning

Unsupervised Hierarchical Semantic Segmentation With Multiview Cosegmentation and Clustering Transformers

Cut and Learn for Unsupervised Object Detection and Instance Segmentation

Bootstrapping Objectness From Videos by Relaxed Common Fate and Visual Grouping

Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression

Unsupervised Learning of Important Objects From First-Person Videos

Am I a Baller? Basketball Performance Assessment From First-Person Videos

SegSort: Segmentation by Discriminative Sorting of Segments

Learning to Transform for Generalizable Instance-wise Invariance

Unsupervised Sketch to Photo Synthesis

Unsupervised Selective Labeling for More Effective Semi-Supervised Learning

Open Ad-hoc Categorization with Contextualized Feature Learning

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

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

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