Search Results for author:
Found 25 papers, 14 papers with code
FairCLIP: Harnessing Fairness in Vision-Language Learning
Fairness is a critical concern in deep learning, especially in healthcare, where these models influence diagnoses and treatment decisions.
3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors
Specifically, it is powered by a text-conditioned tri-plane latent diffusion model, which quickly generates coarse 3D samples for fast prototyping.
FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scaling
Existing medical fairness datasets are all for classification tasks, and no fairness datasets are available for medical segmentation, while medical segmentation is an equally important clinical task as classifications, which can provide detailed spatial information on organ abnormalities ready to be assessed by clinicians.
FairVision: Equitable Deep Learning for Eye Disease Screening via Fair Identity Scaling
To address this research gap, we conduct the first comprehensive study on the fairness of 3D medical imaging models across multiple protected attributes.
When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo
This constraint reduces the 2D search space into the epipolar line in stereo matching.
Ranked #3 on
3D Reconstruction
on DTU
EANet: Expert Attention Network for Online Trajectory Prediction
We introduce expert attention, which adjusts the weights of different depths of network layers, avoiding the model updated slowly due to gradient problem and enabling fast learning of new scenario's knowledge to restore prediction accuracy.
Harvard Glaucoma Detection and Progression: A Multimodal Multitask Dataset and Generalization-Reinforced Semi-Supervised Learning
This is the largest glaucoma detection dataset with 3D OCT imaging data and the first glaucoma progression forecasting dataset that is publicly available.
The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World
We present the All-Seeing (AS) project: a large-scale data and model for recognizing and understanding everything in the open world.
Neural Video Depth Stabilizer
Video depth estimation aims to infer temporally consistent depth.
Ranked #16 on
Monocular Depth Estimation
on NYU-Depth V2
(using extra training data)
Harvard Glaucoma Fairness: A Retinal Nerve Disease Dataset for Fairness Learning and Fair Identity Normalization
To address this gap, we introduce Harvard Glaucoma Fairness (Harvard-GF), a retinal nerve disease dataset with both 2D and 3D imaging data and balanced racial groups for glaucoma detection.
Matching Is Not Enough: A Two-Stage Framework for Category-Agnostic Pose Estimation
To calibrate the inaccurate matching results, we introduce a two-stage framework, where matched keypoints from the first stage are viewed as similarity-aware position proposals.
Ranked #3 on
2D Pose Estimation
on MP-100
Demystify Transformers & Convolutions in Modern Image Deep Networks
Our experiments on various tasks and an analysis of inductive bias show a significant performance boost due to advanced network-level and block-level designs, but performance differences persist among different STMs.
Artifact-Tolerant Clustering-Guided Contrastive Embedding Learning for Ophthalmic Images
Ophthalmic images and derivatives such as the retinal nerve fiber layer (RNFL) thickness map are crucial for detecting and monitoring ophthalmic diseases (e. g., glaucoma).
Design What You Desire: Icon Generation from Orthogonal Application and Theme Labels
Generative adversarial networks (GANs) have been trained to be professional artists able to create stunning artworks such as face generation and image style transfer.
3D Instances as 1D Kernels
The idea of instance kernel is inspired by recent success of dynamic convolutions in 2D/3D instance segmentation.
Ranked #2 on
3D Instance Segmentation
on S3DIS
(mCov metric)
Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting
In this work, we propose a similarity-aware CAC framework that jointly learns representation and similarity metric.
Ranked #4 on
Object Counting
on CARPK
ST-PCNN: Spatio-Temporal Physics-Coupled Neural Networks for Dynamics Forecasting
A spatio-temporal physics-coupled neural network (ST-PCNN) model is proposed to achieve three goals: (1) learning the underlying physics parameters, (2) transition of local information between spatio-temporal regions, and (3) forecasting future values for the dynamical system.
Physics-Coupled Spatio-Temporal Active Learning for Dynamical Systems
To tackle these challenges, we advocate a spatio-temporal physics-coupled neural networks (ST-PCNN) model to learn the underlying physics of the dynamical system and further couple the learned physics to assist the learning of the recurring dynamics.
Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report
While many solutions have been proposed for this task, they are usually very computationally expensive and thus are not applicable for on-device inference.
Deep Attributed Network Representation Learning via Attribute Enhanced Neighborhood
In this paper, we propose a deep attributed network representation learning via attribute enhanced neighborhood (DANRL-ANE) model to improve the robustness and effectiveness of node representations.
Evolutionary Architecture Search for Graph Neural Networks
In particular, Neural Architecture Search (NAS) has seen significant attention throughout the AutoML research community, and has pushed forward the state-of-the-art in a number of neural models to address grid-like data such as texts and images.
Deep Line Art Video Colorization with a Few References
The color transform network takes the target line art images as well as the line art and color images of one or more reference images as input, and generates corresponding target color images.
Multi-Label Graph Convolutional Network Representation Learning
The multi-label network nodes not only have multiple labels for each node, such labels are often highly correlated making existing methods ineffective or fail to handle such correlation for node representation learning.
Ranked #30 on
Multi-Label Classification
on MS-COCO
Feature-Attention Graph Convolutional Networks for Noise Resilient Learning
By using spectral-based graph convolution aggregation process, each node is allowed to concentrate more on the most determining neighborhood features aligned with the corresponding learning task.
DOT: Gene-set analysis by combining decorrelated association statistics
Historically, the majority of statistical association methods have been designed assuming availability of SNP-level information.
Genomics Applications
