174 citations · 711 across the 57 of their papers we have counts for
49 papers · 1 filter
Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping
Long Lian, Zhirong Wu, Stella X. Yu
We study learning object segmentation from unlabeled videos. Humans can easily segment moving objects without knowing what they are. The Gestalt law of common fate, i.e., what move…
Cut and Learn for Unsupervised Object Detection and Instance Segmentation
Xudong Wang, Rohit Girdhar, Stella X. Yu +1
We propose Cut-and-LEaRn (CutLER), a simple approach for training unsupervised object detection and segmentation models. We leverage the property of self-supervised models to 'disc…
Improving Unsupervised Video Object Segmentation with Motion-Appearance Synergy
Long Lian, Zhirong Wu, Stella X. Yu
We present IMAS, a method that segments the primary objects in videos without manual annotation in training or inference. Previous methods in unsupervised video object segmentation…
Multi-Spectral Image Classification with Ultra-Lean Complex-Valued Models
Utkarsh Singhal, Stella X. Yu, Zackery Steck +2
Multi-spectral imagery is invaluable for remote sensing due to different spectral signatures exhibited by materials that often appear identical in greyscale and RGB imagery. Paired…
Learning Hierarchical Image Segmentation For Recognition and By Recognition
Tsung-Wei Ke, Sangwoo Mo, Stella X. Yu
Large vision and language models learned directly through image-text associations often lack detailed visual substantiation, whereas image segmentation tasks are treated separately…
Unsupervised Scene Sketch to Photo Synthesis
Jiayun Wang, Sangryul Jeon, Stella X. Yu +3
Sketches make an intuitive and powerful visual expression as they are fast executed freehand drawings. We present a method for synthesizing realistic photos from scene sketches. Wi…
Open Long-Tailed Recognition in a Dynamic World
Ziwei Liu, Zhongqi Miao, Xiaohang Zhan +3
Real world data often exhibits a long-tailed and open-ended (with unseen classes) distribution. A practical recognition system must balance between majority (head) and minority (ta…
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…
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…
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…
Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning
Tsung-Wei Ke, Jyh-Jing Hwang, Stella X. Yu
Weakly supervised segmentation requires assigning a label to every pixel based on training instances with partial annotations such as image-level tags, object bounding boxes, label…
Iterative Human and Automated Identification of Wildlife Images
Zhongqi Miao, Ziwei Liu, Kaitlyn M. Gaynor +3
Camera trapping is increasingly used to monitor wildlife, but this technology typically requires extensive data annotation. Recently, deep learning has significantly advanced autom…
Unsupervised deep learning for grading of age-related macular degeneration using retinal fundus images
Baladitya Yellapragada, Sascha Hornhauer, Kiersten Snyder +2
Many diseases are classified based on human-defined rubrics that are prone to bias. Supervised neural networks can automate the grading of retinal fundus images, but require labor-…
Long-tailed Recognition by Routing Diverse Distribution-Aware Experts
Xudong Wang, Long Lian, Zhongqi Miao +2
Natural data are often long-tail distributed over semantic classes. Existing recognition methods tackle this imbalanced classification by placing more emphasis on the tail data, th…
Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters
Xudong Wang, Stella X. Yu
Convolution is the main building block of convolutional neural networks (CNN). We observe that an optimized CNN often has highly correlated filters as the number of channels increa…
Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination
Xudong Wang, Ziwei Liu, Stella X. Yu
Unsupervised feature learning has made great strides with contrastive learning based on instance discrimination and invariant mapping, as benchmarked on curated class-balanced data…
BatVision with GCC-PHAT Features for Better Sound to Vision Predictions
Jesper Haahr Christensen, Sascha Hornauer, Stella Yu
Inspired by sophisticated echolocation abilities found in nature, we train a generative adversarial network to predict plausible depth maps and grayscale layouts from sound. To ach…
3D Shape Reconstruction from Free-Hand Sketches
Jiayun Wang, Jierui Lin, Qian Yu +3
Sketches are the most abstract 2D representations of real-world objects. Although a sketch usually has geometrical distortion and lacks visual cues, humans can effortlessly envisio…
BatVision: Learning to See 3D Spatial Layout with Two Ears
Jesper Haahr Christensen, Sascha Hornauer, Stella Yu
Many species have evolved advanced non-visual perception while artificial systems fall behind. Radar and ultrasound complement camera-based vision but they are often too costly and…
Orthogonal Convolutional Neural Networks
Jiayun Wang, Yubei Chen, Rudrasis Chakraborty +1
Deep convolutional neural networks are hindered by training instability and feature redundancy towards further performance improvement. A promising solution is to impose orthogonal…
POIRot: A rotation invariant omni-directional pointnet
Liu Yang, Rudrasis Chakraborty, Stella X. Yu
Point-cloud is an efficient way to represent 3D world. Analysis of point-cloud deals with understanding the underlying 3D geometric structure. But due to the lack of smooth topolog…
SegSort: Segmentation by Discriminative Sorting of Segments
Jyh-Jing Hwang, Stella X. Yu, Jianbo Shi +4
Almost all existing deep learning approaches for semantic segmentation tackle this task as a pixel-wise classification problem. Yet humans understand a scene not in terms of pixels…
SurReal: Complex-Valued Learning as Principled Transformations on a Scaling and Rotation Manifold
Rudrasis Chakraborty, Yifei Xing, Stella Yu
Complex-valued data is ubiquitous in signal and image processing applications, and complex-valued representations in deep learning have appealing theoretical properties. While thes…
Building Information Modeling and Classification by Visual Learning At A City Scale
Qian Yu, Chaofeng Wang, Barbaros Cetiner +4
In this paper, we provide two case studies to demonstrate how artificial intelligence can empower civil engineering. In the first case, a machine learning-assisted framework, BRAIL…