Search Results for author:
Found 60 papers, 35 papers with code
Learning Important Spatial Pooling Regions for Scene Classification
We address the false response influence problem when learning and applying discriminative parts to construct the mid-level representation in scene classification.
Bounded-Distortion Metric Learning
Metric learning aims to embed one metric space into another to benefit tasks like classification and clustering.
Handling Motion Blur in Multi-Frame Super-Resolution
Ubiquitous motion blur easily fails multi-frame super-resolution (MFSR).
Learning to Generate Images with Perceptual Similarity Metrics
We propose instead to use a loss function that is better calibrated to human perceptual judgments of image quality: the multiscale structural-similarity score (MS-SSIM).
Video Super-Resolution via Deep Draft-Ensemble Learning
We propose a new direction for fast video super-resolution (VideoSR) via a SR draft ensemble, which is defined as the set of high-resolution patch candidates before final image deconvolution.
Semantic Segmentation With Object Clique Potential
In this paper, we propose an object clique potential for semantic segmentation.
Normalizing the Normalizers: Comparing and Extending Network Normalization Schemes
On the other hand, layer normalization normalizes the activations across all activities within a layer.
Learning Deep Parsimonious Representations
In this paper we aim at facilitating generalization for deep networks while supporting interpretability of the learned representations.
Detail-revealing Deep Video Super-resolution
In this paper, we show that proper frame alignment and motion compensation is crucial for achieving high quality results.
Ranked #11 on
Video Super-Resolution
on Vid4 - 4x upscaling
Situation Recognition with Graph Neural Networks
We address the problem of recognizing situations in images.
Ranked #9 on
Situation Recognition
on imSitu
3D Graph Neural Networks for RGBD Semantic Segmentation
Each node in the graph corresponds to a set of points and is associated with a hidden representation vector initialized with an appearance feature extracted by a unary CNN from 2D images.
Ranked #30 on
Semantic Segmentation
on SUN-RGBD
(using extra training data)
NerveNet: Learning Structured Policy with Graph Neural Networks
We address the problem of learning structured policies for continuous control.
Understanding Short-Horizon Bias in Stochastic Meta-Optimization
Careful tuning of the learning rate, or even schedules thereof, can be crucial to effective neural net training.
Graph Partition Neural Networks for Semi-Supervised Classification
We present graph partition neural networks (GPNN), an extension of graph neural networks (GNNs) able to handle extremely large graphs.
Reviving and Improving Recurrent Back-Propagation
We examine all RBP variants along with BPTT and TBPTT in three different application domains: associative memory with continuous Hopfield networks, document classification in citation networks using graph neural networks and hyperparameter optimization for fully connected networks.
Learning deep structured active contours end-to-end
The world is covered with millions of buildings, and precisely knowing each instance's position and extents is vital to a multitude of applications.
Inference in Probabilistic Graphical Models by Graph Neural Networks
Message-passing algorithms, such as belief propagation, are a natural way to disseminate evidence amongst correlated variables while exploiting the graph structure, but these algorithms can struggle when the conditional dependency graphs contain loops.
GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation
In this paper, we propose Geometric Neural Network (GeoNet) to jointly predict depth and surface normal maps from a single image.
Neural Guided Constraint Logic Programming for Program Synthesis
Synthesizing programs using example input/outputs is a classic problem in artificial intelligence.
Incremental Few-Shot Learning with Attention Attractor Networks
This paper addresses this problem, incremental few-shot learning, where a regular classification network has already been trained to recognize a set of base classes, and several extra novel classes are being considered, each with only a few labeled examples.
LanczosNet: Multi-Scale Deep Graph Convolutional Networks
We propose the Lanczos network (LanczosNet), which uses the Lanczos algorithm to construct low rank approximations of the graph Laplacian for graph convolution.
UPSNet: A Unified Panoptic Segmentation Network
More importantly, we introduce a parameter-free panoptic head which solves the panoptic segmentation via pixel-wise classification.
Ranked #3 on
Panoptic Segmentation
on Indian Driving Dataset
DARNet: Deep Active Ray Network for Building Segmentation
In this paper, we propose a Deep Active Ray Network (DARNet) for automatic building segmentation.
Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models
We introduce a new molecular dataset, named Alchemy, for developing machine learning models useful in chemistry and material science.
Deformable Filter Convolution for Point Cloud Reasoning
Point clouds are the native output of many real-world 3D sensors.
ASYNCHRONOUS MULTI-AGENT GENERATIVE ADVERSARIAL IMITATION LEARNING
Imitation learning aims to inversely learn a policy from expert demonstrations, which has been extensively studied in the literature for both single-agent setting with Markov decision process (MDP) model, and multi-agent setting with Markov game (MG) model.
DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation
In practice, it performs similarly to the Hungarian algorithm during inference.
Efficient Graph Generation with Graph Recurrent Attention Networks
Our model generates graphs one block of nodes and associated edges at a time.
Discrete Residual Flow for Probabilistic Pedestrian Behavior Prediction
Particularly difficult is the prediction of human behavior.
Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data
A graph neural network then iteratively updates the actor states via a message passing process.
Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving
Feedforward computation, such as evaluating a neural network or sampling from an autoregressive model, is ubiquitous in machine learning.
Latent Variable Modelling with Hyperbolic Normalizing Flows
One effective solution is the use of normalizing flows \cut{defined on Euclidean spaces} to construct flexible posterior distributions.
Fast and Accurate: Structure Coherence Component for Face Alignment
In this paper, we propose a fast and accurate coordinate regression method for face alignment.
Ranked #15 on
Face Alignment
on COFW
Implicit Latent Variable Model for Scene-Consistent Motion Forecasting
In order to plan a safe maneuver an autonomous vehicle must accurately perceive its environment, and understand the interactions among traffic participants.
Learning Lane Graph Representations for Motion Forecasting
We propose a motion forecasting model that exploits a novel structured map representation as well as actor-map interactions.
DSDNet: Deep Structured self-Driving Network
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.
Testing the Safety of Self-driving Vehicles by Simulating Perception and Prediction
We present a novel method for testing the safety of self-driving vehicles in simulation.
GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation
Note that GeoNet++ is generic and can be used in other depth/normal prediction frameworks to improve the quality of 3D reconstruction and pixel-wise accuracy of depth and surface normals.
A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks
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 (MPGNNs), via a PAC-Bayesian approach.
Safety-Oriented Pedestrian Motion and Scene Occupancy Forecasting
On two large-scale real-world datasets, nuScenes and ATG4D, we showcase that our scene-occupancy predictions are more accurate and better calibrated than those from state-of-the-art motion forecasting methods, while also matching their performance in pedestrian motion forecasting metrics.
LookOut: Diverse Multi-Future Prediction and Planning for Self-Driving
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 trajectory of the SDV by optimizing a set of contingency plans over these future realizations.
LaneRCNN: Distributed Representations for Graph-Centric Motion Forecasting
In this paper, we propose LaneRCNN, a graph-centric motion forecasting model.
Ranked #150 on
Motion Forecasting
on Argoverse CVPR 2020
NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation
1) We propose a non-parametric prior distribution over the appearance of image parts so that the latent variable ``what-to-draw'' per step becomes a categorical random variable.
NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds
We introduce a method for instance proposal generation for 3D point clouds.
EchoGNN: Explainable Ejection Fraction Estimation with Graph Neural Networks
In this work, we introduce EchoGNN, a model based on graph neural networks (GNNs) to estimate EF from echo videos.
Scaling Forward Gradient With Local Losses
Forward gradient learning computes a noisy directional gradient and is a biologically plausible alternative to backprop for learning deep neural networks.
Gaussian-Bernoulli RBMs Without Tears
We revisit the challenging problem of training Gaussian-Bernoulli restricted Boltzmann machines (GRBMs), introducing two innovations.
VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge
In contrast to previous methods which inject knowledge from static knowledge bases, we investigate the incorporation of contextualized knowledge using Commonsense Transformer (COMET), an existing knowledge model trained on human-curated knowledge bases.
Ranked #8 on
Visual Question Answering (VQA)
on A-OKVQA
(DA VQA Score metric)
Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks
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 search) from input-output pairs using deep neural networks.
Learning Latent Part-Whole Hierarchies for Point Clouds
The decoder takes the latent variable and the feature from the encoder as an input and predicts the per-point part distribution at the top level.
GraphPNAS: Learning Distribution of Good Neural Architectures via Deep Graph Generative Models
Moreover, our graph generator leads to a learnable probabilistic search method that is more flexible and efficient than the commonly used RNN generator and random search methods.
Self-Supervised Relation Alignment for Scene Graph Generation
In the auxiliary branch, relational input features are partially masked prior to message passing and predicate prediction.
Specformer: Spectral Graph Neural Networks Meet Transformers
To tackle these issues, we introduce Specformer, which effectively encodes the set of all eigenvalues and performs self-attention in the spectral domain, leading to a learnable set-to-set spectral filter.
Memorization Capacity of Multi-Head Attention in Transformers
Transformers have become the go-to architecture for language and vision tasks, yet their theoretical properties, especially memorization capacity, remain elusive.
SwinGNN: Rethinking Permutation Invariance in Diffusion Models for Graph Generation
Diffusion models based on permutation-equivariant networks can learn permutation-invariant distributions for graph data.
EchoGLAD: Hierarchical Graph Neural Networks for Left Ventricle Landmark Detection on Echocardiograms
To address this challenge, we introduce an echocardiogram-based, hierarchical graph neural network (GNN) for left ventricle landmark detection (EchoGLAD).
GEMTrans: A General, Echocardiography-based, Multi-Level Transformer Framework for Cardiovascular Diagnosis
Due to inter-observer variability in echo-based diagnosis, which arises from the variability in echo image acquisition and the interpretation of echo images based on clinical experience, vision-based machine learning (ML) methods have gained popularity to act as secondary layers of verification.
Joint Generative Modeling of Scene Graphs and Images via Diffusion Models
While previous works have explored image generation conditioned on scene graphs or layouts, our task is distinctive and important as it involves generating scene graphs themselves unconditionally from noise, enabling efficient and interpretable control for image generation.
Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing
Subsequently, we transform the point cloud using the latent poses, feeding it to the part encoder for aggregating super-part information and reasoning about part relationships to predict all part poses.
An Information-Theoretic Framework for Out-of-Distribution Generalization
We study the Out-of-Distribution (OOD) generalization in machine learning and propose a general framework that provides information-theoretic generalization bounds.
