
Balancing Constraints and Submodularity in Data Subset Selection
Deep learning has yielded extraordinary results in vision and natural la...
read it

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...
read it

Scaling Up Exact Neural Network Compression by ReLU Stability
We can compress a neural network while exactly preserving its underlying...
read it

Mapping of Sparse 3D Data using Alternating Projection
We propose a novel technique to register sparse 3D scans in the absence ...
read it

Lossless Compression of Deep Neural Networks
Deep neural networks have been successful in many predictive modeling ta...
read it

Can generalised relative pose estimation solve sparse 3D registration?
Popular 3D scan registration projects, such as Stanford digital Michelan...
read it

Equivalent and Approximate Transformations of Deep Neural Networks
Two networks are equivalent if they produce the same output for any give...
read it

Minimal Solvers for MiniLoop Closures in 3D MultiScan Alignment
3D scan registration is a classical, yet a highly useful problem in the ...
read it

3DRegNet: A Deep Neural Network for 3D Point Registration
We present 3DRegNet, a deep learning algorithm for the registration of 3...
read it

Novel Single View Constraints for Manhattan 3D Line Reconstruction
This paper proposes a novel and exact method to reconstruct linebased 3...
read it

Empirical Bounds on Linear Regions of Deep Rectifier Networks
One form of characterizing the expressiveness of a piecewise linear neur...
read it

Simultaneous Edge Alignment and Learning
Edge detection is among the most fundamental vision problems for its rol...
read it

A Minimal ClosedForm Solution for MultiPerspective Pose Estimation using Points and Lines
We propose a minimal solution for pose estimation using both points and ...
read it

VLASE: Vehicle Localization by Aggregating Semantic Edges
In this paper, we propose VLASE, a framework to use semantic edge featur...
read it

How Could Polyhedral Theory Harness Deep Learning?
The holy grail of deep learning is to come up with an automatic method t...
read it

Building Anatomically Realistic Jaw Kinematics Model from Data
This paper considers a different aspect of anatomical face modeling: kin...
read it

Analytical Modeling of Vanishing Points and Curves in Catadioptric Cameras
Vanishing points and vanishing lines are classical geometrical concepts ...
read it

Learning Strict Identity Mappings in Deep Residual Networks
A family of super deep networks, referred to as residual networks or Res...
read it

Class Subset Selection for Transfer Learning using Submodularity
In recent years, it is common practice to extract fullyconnected layer ...
read it

Bounding and Counting Linear Regions of Deep Neural Networks
In this paper, we study the representational power of deep neural networ...
read it

Submodular Function Maximization for Group Elevator Scheduling
We propose a novel approach for group elevator scheduling by formulating...
read it

CASENet: Deep CategoryAware Semantic Edge Detection
Boundary and edge cues are highly beneficial in improving a wide variety...
read it

Layered Interpretation of Street View Images
We propose a layered street view model to encode both depth and semantic...
read it

Efficient Minimization of Higher Order Submodular Functions using Monotonic Boolean Functions
Submodular function minimization is a key problem in a wide variety of a...
read it
Srikumar Ramalingam
is this you? claim profile