research
∙
01/28/2023
Leveraging Importance Weights in Subset Selection
We present a subset selection algorithm designed to work with arbitrary ...
share
research
∙
10/28/2022
When does mixup promote local linearity in learned representations?
Mixup is a regularization technique that artificially produces new sampl...
research
∙
03/09/2022
The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks
Neural networks tend to achieve better accuracy with training if they ar...
research
∙
06/10/2021
Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifold
Single image pose estimation is a fundamental problem in many vision and...
research
∙
05/19/2021
Balancing Robustness and Sensitivity using Feature Contrastive Learning
It is generally believed that robust training of extremely large network...
research
∙
04/26/2021
Balancing Constraints and Submodularity in Data Subset Selection
Deep learning has yielded extraordinary results in vision and natural la...
research
∙
03/04/2021
There and back again: Cycle consistency across sets for isolating factors of variation
Representational learning hinges on the task of unraveling the set of un...
research
∙
02/15/2021
Scaling Up Exact Neural Network Compression by ReLU Stability
We can compress a neural network while exactly preserving its underlying...
research
∙
10/04/2020
Mapping of Sparse 3D Data using Alternating Projection
We propose a novel technique to register sparse 3D scans in the absence ...
research
∙
01/01/2020
Lossless Compression of Deep Neural Networks
Deep neural networks have been successful in many predictive modeling ta...
research
∙
06/13/2019
Can generalised relative pose estimation solve sparse 3D registration?
Popular 3D scan registration projects, such as Stanford digital Michelan...
research
∙
05/27/2019
Equivalent and Approximate Transformations of Deep Neural Networks
Two networks are equivalent if they produce the same output for any give...
research
∙
04/08/2019
Minimal Solvers for Mini-Loop Closures in 3D Multi-Scan Alignment
3D scan registration is a classical, yet a highly useful problem in the ...
research
∙
04/02/2019
3DRegNet: A Deep Neural Network for 3D Point Registration
We present 3DRegNet, a deep learning algorithm for the registration of 3...
research
∙
10/08/2018
Novel Single View Constraints for Manhattan 3D Line Reconstruction
This paper proposes a novel and exact method to reconstruct line-based 3...
research
∙
10/08/2018
Empirical Bounds on Linear Regions of Deep Rectifier Networks
One form of characterizing the expressiveness of a piecewise linear neur...
research
∙
08/06/2018
Simultaneous Edge Alignment and Learning
Edge detection is among the most fundamental vision problems for its rol...
research
∙
07/26/2018
A Minimal Closed-Form Solution for Multi-Perspective Pose Estimation using Points and Lines
We propose a minimal solution for pose estimation using both points and ...
research
∙
07/06/2018
VLASE: Vehicle Localization by Aggregating Semantic Edges
In this paper, we propose VLASE, a framework to use semantic edge featur...
research
∙
06/17/2018
How Could Polyhedral Theory Harness Deep Learning?
The holy grail of deep learning is to come up with an automatic method t...
research
∙
05/15/2018
Building Anatomically Realistic Jaw Kinematics Model from Data
This paper considers a different aspect of anatomical face modeling: kin...
research
∙
04/25/2018
Analytical Modeling of Vanishing Points and Curves in Catadioptric Cameras
Vanishing points and vanishing lines are classical geometrical concepts ...
research
∙
04/05/2018
Learning Strict Identity Mappings in Deep Residual Networks
A family of super deep networks, referred to as residual networks or Res...
research
∙
03/30/2018
Class Subset Selection for Transfer Learning using Submodularity
In recent years, it is common practice to extract fully-connected layer ...
research
∙
11/06/2017
Bounding and Counting Linear Regions of Deep Neural Networks
In this paper, we study the representational power of deep neural networ...
research
∙
06/28/2017
Submodular Function Maximization for Group Elevator Scheduling
We propose a novel approach for group elevator scheduling by formulating...
research
∙
05/27/2017
CASENet: Deep Category-Aware Semantic Edge Detection
Boundary and edge cues are highly beneficial in improving a wide variety...
research
∙
06/15/2015
Layered Interpretation of Street View Images
We propose a layered street view model to encode both depth and semantic...
research
∙
09/11/2011