183 citations · 1.2k across the 45 of their papers we have counts for
48 papers
GEMTrans: A General, Echocardiography-based, Multi-Level Transformer Framework for Cardiovascular Diagnosis
Masoud Mokhtari, Neda Ahmadi, Teresa S. M. Tsang +2
Echocardiography (echo) is an ultrasound imaging modality that is widely used for various cardiovascular diagnosis tasks. Due to inter-observer variability in echo-based diagnosis,…
EchoGLAD: Hierarchical Graph Neural Networks for Left Ventricle Landmark Detection on Echocardiograms
Masoud Mokhtari, Mobina Mahdavi, Hooman Vaseli +4
The functional assessment of the left ventricle chamber of the heart requires detecting four landmark locations and measuring the internal dimension of the left ventricle and the a…
SwinGNN: Rethinking Permutation Invariance in Diffusion Models for Graph Generation
Qi Yan, Zhengyang Liang, Yang Song +2
Diffusion models based on permutation-equivariant networks can learn permutation-invariant distributions for graph data. However, in comparison to their non-invariant counterparts,…
Memorization Capacity of Multi-Head Attention in Transformers
Sadegh Mahdavi, Renjie Liao, Christos Thrampoulidis
Transformers have become the go-to architecture for language and vision tasks, yet their theoretical properties, especially memorization capacity, remain elusive. This paper invest…
Specformer: Spectral Graph Neural Networks Meet Transformers
Deyu Bo, Chuan Shi, Lele Wang +1
Spectral graph neural networks (GNNs) learn graph representations via spectral-domain graph convolutions. However, most existing spectral graph filters are scalar-to-scalar functio…
Self-Supervised Relation Alignment for Scene Graph Generation
Bicheng Xu, Renjie Liao, Leonid Sigal
The goal of scene graph generation is to predict a graph from an input image, where nodes correspond to identified and localized objects and edges to their corresponding interactio…
GraphPNAS: Learning Distribution of Good Neural Architectures via Deep Graph Generative Models
Muchen Li, Jeffrey Yunfan Liu, Leonid Sigal +1
Neural architectures can be naturally viewed as computational graphs. Motivated by this perspective, we, in this paper, study neural architecture search (NAS) through the lens of l…
Learning Latent Part-Whole Hierarchies for Point Clouds
Xiang Gao, Wei Hu, Renjie Liao
Strong evidence suggests that humans perceive the 3D world by parsing visual scenes and objects into part-whole hierarchies. Although deep neural networks have the capability of le…
Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks
Sadegh Mahdavi, Kevin Swersky, Thomas Kipf +3
In this paper, we study the OOD generalization of neural algorithmic reasoning tasks, where the goal is to learn an algorithm (e.g., sorting, breadth-first search, and depth-first…
VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge
Sahithya Ravi, Aditya Chinchure, Leonid Sigal +2
There has been a growing interest in solving Visual Question Answering (VQA) tasks that require the model to reason beyond the content present in the image. In this work, we focus…
Gaussian-Bernoulli RBMs Without Tears
Renjie Liao, Simon Kornblith, Mengye Ren +2
We revisit the challenging problem of training Gaussian-Bernoulli restricted Boltzmann machines (GRBMs), introducing two innovations. We propose a novel Gibbs-Langevin sampling alg…
Scaling Forward Gradient With Local Losses
Mengye Ren, Simon Kornblith, Renjie Liao +1
Forward gradient learning computes a noisy directional gradient and is a biologically plausible alternative to backprop for learning deep neural networks. However, the standard for…
EchoGNN: Explainable Ejection Fraction Estimation with Graph Neural Networks
Masoud Mokhtari, Teresa Tsang, Purang Abolmaesumi +1
Ejection fraction (EF) is a key indicator of cardiac function, allowing identification of patients prone to heart dysfunctions such as heart failure. EF is estimated from cardiac u…
NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds
Weiwei Sun, Daniel Rebain, Renjie Liao +4
We introduce a method for instance proposal generation for 3D point clouds. Existing techniques typically directly regress proposals in a single feed-forward step, leading to inacc…
NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation
Xiaohui Zeng, Raquel Urtasun, Richard Zemel +2
In this paper, we present a non-parametric structured latent variable model for image generation, called NP-DRAW, which sequentially draws on a latent canvas in a part-by-part fash…
LaneRCNN: Distributed Representations for Graph-Centric Motion Forecasting
Wenyuan Zeng, Ming Liang, Renjie Liao +1
Forecasting the future behaviors of dynamic actors is an important task in many robotics applications such as self-driving. It is extremely challenging as actors have latent intent…
Safety-Oriented Pedestrian Motion and Scene Occupancy Forecasting
Katie Luo, Sergio Casas, Renjie Liao +4
In this paper, we address the important problem in self-driving of forecasting multi-pedestrian motion and their shared scene occupancy map, critical for safe navigation. Our contr…
LookOut: Diverse Multi-Future Prediction and Planning for Self-Driving
Alexander Cui, Sergio Casas, Abbas Sadat +2
In this paper, we present LookOut, a novel autonomy system that perceives the environment, predicts a diverse set of futures of how the scene might unroll and estimates the traject…
A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks
Renjie Liao, Raquel Urtasun, Richard Zemel
In this paper, we derive generalization bounds for the two primary classes of graph neural networks (GNNs), namely graph convolutional networks (GCNs) and message passing GNNs (MPG…
GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation
Xiaojuan Qi, Zhengzhe Liu, Renjie Liao +3
In this paper, we propose a geometric neural network with edge-aware refinement (GeoNet++) to jointly predict both depth and surface normal maps from a single image. Building on to…
DSDNet: Deep Structured self-Driving Network
Wenyuan Zeng, Shenlong Wang, Renjie Liao +3
In this paper, we propose the Deep Structured self-Driving Network (DSDNet), which performs object detection, motion prediction, and motion planning with a single neural network. T…
Testing the Safety of Self-driving Vehicles by Simulating Perception and Prediction
Kelvin Wong, Qiang Zhang, Ming Liang +4
We present a novel method for testing the safety of self-driving vehicles in simulation. We propose an alternative to sensor simulation, as sensor simulation is expensive and has l…
Learning Lane Graph Representations for Motion Forecasting
Ming Liang, Bin Yang, Rui Hu +4
We propose a motion forecasting model that exploits a novel structured map representation as well as actor-map interactions. Instead of encoding vectorized maps as raster images, w…
Implicit Latent Variable Model for Scene-Consistent Motion Forecasting
Sergio Casas, Cole Gulino, Simon Suo +3
In order to plan a safe maneuver an autonomous vehicle must accurately perceive its environment, and understand the interactions among traffic participants. In this paper, we aim t…