
Generating Adversarial Examples with Graph Neural Networks
Recent years have witnessed the deployment of adversarial attacks to eva...
read it

Comment on Stochastic Polyak StepSize: Performance of ALIG
This is a short note on the performance of the ALIG algorithm (Berrada ...
read it

Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition
We improve the scalability of Branch and Bound (BaB) algorithms for form...
read it

Verifying Probabilistic Specifications with Functional Lagrangians
We propose a general framework for verifying inputoutput specifications...
read it

Scaling the Convex Barrier with Active Sets
Tight and efficient neural network bounding is of critical importance fo...
read it

Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instances
Recent approaches for weakly supervised instance segmentations depend on...
read it

Hybrid Models for Learning to Branch
A recent Graph Neural Network (GNN) approach for learning to branch has ...
read it

Lagrangian Decomposition for Neural Network Verification
A fundamental component of neural network verification is the computatio...
read it

Neural Network Branching for Neural Network Verification
Formal verification of neural networks is essential for their deployment...
read it

Branch and Bound for Piecewise Linear Neural Network Verification
The success of Deep Learning and its potential use in many safetycritic...
read it

Training Neural Networks for and by Interpolation
The majority of modern deep learning models are able to interpolate the ...
read it

Dissimilarity Coefficient based Weakly Supervised Object Detection
We consider the problem of weakly supervised object detection, where the...
read it

Deep FrankWolfe For Neural Network Optimization
Learning a deep neural network requires solving a challenging optimizati...
read it

Statistical Verification of Neural Networks
We present a new approach to neural network verification based on estima...
read it

Learning Human Poses from Actions
We consider the task of learning to estimate human pose in still images....
read it

Efficient Relaxations for Dense CRFs with Sparse Higher Order Potentials
Dense conditional random fields (CRFs) with Gaussian pairwise potentials...
read it

Smooth Loss Functions for Deep Topk Classification
The topk error is a common measure of performance in machine learning a...
read it

Worstcase Optimal Submodular Extensions for Marginal Estimation
Submodular extensions of an energy function can be used to efficiently c...
read it

Coplanar Repeats by Energy Minimization
This paper proposes an automated method to detect, group and rectify arb...
read it

Piecewise Linear Neural Network verification: A comparative study
The success of Deep Learning and its potential use in many important saf...
read it

Efficient Linear Programming for Dense CRFs
The fully connected conditional random field (CRF) with Gaussian pairwis...
read it

Trusting SVM for Piecewise Linear CNNs
We present a novel layerwise optimization algorithm for the learning obj...
read it

Efficient Continuous Relaxations for Dense CRF
Dense conditional random fields (CRF) with Gaussian pairwise potentials ...
read it

DISCO Nets: DISsimilarity COefficient Networks
We present a new type of probabilistic model which we call DISsimilarity...
read it

Truncated MaxofConvex Models
Truncated convex models (TCM) are a special case of pairwise random fiel...
read it

Parsimonious Labeling
We propose a new family of discrete energy minimization problems, which ...
read it

Discriminative Parameter Estimation for Random Walks Segmentation
The Random Walks (RW) algorithm is one of the most e  cient and easyto...
read it

Discriminative Parameter Estimation for Random Walks Segmentation: Technical Report
The Random Walks (RW) algorithm is one of the most e  cient and easyto...
read it

Modeling Latent Variable Uncertainty for Lossbased Learning
We consider the problem of parameter estimation using weakly supervised ...
read it

MAP Estimation of SemiMetric MRFs via Hierarchical Graph Cuts
We consider the task of obtaining the maximum a posteriori estimate of d...
read it
M. Pawan Kumar
verfied profile
Associate Professor in the Department of Engineering Science at the University of Oxford, Principal researcher in the OVAL group.