Search Results for author:
Found 16 papers, 4 papers with code
Local Spectral Graph Convolution for Point Set Feature Learning
In the present article, we propose to overcome this limitation by using spectral graph convolution on a local graph, combined with a novel graph pooling strategy.
Ranked #82 on
3D Point Cloud Classification
on ModelNet40
White matter fiber analysis using kernel dictionary learning and sparsity priors
Results highlight the ability of our method to group streamlines into plausible bundles and illustrate the impact of sparsity priors on the performance of the proposed methods.
Scene Categorization from Contours: Medial Axis Based Salience Measures
That is, the medial axis based salience weights appear to add useful information that is not available when CNNs are trained to use contours alone.
DeepFlux for Skeletons in the Wild
In the present article, we depart from this strategy by training a CNN to predict a two-dimensional vector field, which maps each scene point to a candidate skeleton pixel, in the spirit of flux-based skeletonization algorithms.
Ranked #1 on
Object Skeleton Detection
on SK-LARGE
FAN: Focused Attention Networks
Thus far the learning of attention weights has been driven solely by the minimization of task specific loss functions.
Dominant Set Clustering and Pooling for Multi-View 3D Object Recognition
We improve upon these methods by introducing a view clustering and pooling layer based on dominant sets.
Affinity Graph Supervision for Visual Recognition
Affinity graphs are widely used in deep architectures, including graph convolutional neural networks and attention networks.
Appearance Shock Grammar for Fast Medial Axis Extraction from Real Images
We make the following specific contributions: i) we extend the shock graph representation to the domain of real images, by generalizing the shock type definitions using local, appearance-based criteria; ii) we then use the rules of a Shock Grammar to guide our search for medial points, drastically reducing run time when compared to other methods, which exhaustively consider all points in the input image;iii) we remove the need for typical post-processing steps including thinning, non-maximum suppression, and grouping, by adhering to the Shock Grammar rules while deriving the medial axis solution; iv) finally, we raise some fundamental concerns with the evaluation scheme used in previous work and propose a more appropriate alternative for assessing the performance of medial axis extraction from scenes.
Group Equivariant Deep Reinforcement Learning
In Reinforcement Learning (RL), Convolutional Neural Networks(CNNs) have been successfully applied as function approximators in Deep Q-Learning algorithms, which seek to learn action-value functions and policies in various environments.
Mini-batch graphs for robust image classification
Current deep learning models for classification tasks in computer vision are trained using mini-batches.
EqR: Equivariant Representations for Data-Efficient Reinforcement Learning
We study different notions of equivariance as an inductive bias in Reinforcement Learning (RL) and propose new mechanisms for recovering representations that are equivariant to both an agent’s action, and symmetry transformations of the state-action pairs.
Medial Spectral Coordinates for 3D Shape Analysis
In recent years there has been a resurgence of interest in our community in the shape analysis of 3D objects represented by surface meshes, their voxelized interiors, or surface point clouds.
Average Outward Flux Skeletons for Environment Mapping and Topology Matching
In topology matching between two given maps and their AOF skeletons, we first find correspondences between points on the AOF skeletons of two different environments.
MLGCN: An Ultra Efficient Graph Convolution Neural Model For 3D Point Cloud Analysis
To address these limitations we introduce a novel Multi-level Graph Convolution Neural (MLGCN) model, which uses Graph Neural Networks (GNN) blocks to extract features from 3D point clouds at specific locality levels.
Efficient Dynamics Modeling in Interactive Environments with Koopman Theory
We approach this problem from the lens of Koopman theory, where the nonlinear dynamics of the environment can be linearized in a high-dimensional latent space.
Multimodal and Force-Matched Imitation Learning with a See-Through Visuotactile Sensor
An STS sensor can be switched between visual and tactile modes by leveraging a semi-transparent surface and controllable lighting, allowing for both pre-contact visual sensing and during-contact tactile sensing with a single sensor.
