Puneet K. Dokania

research

∙ 07/09/2021

ANCER: Anisotropic Certification via Sample-wise Volume Maximization

Randomized smoothing has recently emerged as an effective tool that enab...

Francisco Eiras, et al. ∙

research

∙ 04/01/2021

No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks

There has been increasing interest in building deep hierarchy-aware clas...

Shyamgopal Karthik, et al. ∙

research

∙ 12/24/2020

On Batch Normalisation for Approximate Bayesian Inference

We study batch normalisation in the context of variational inference met...

Jishnu Mukhoti, et al. ∙

research

∙ 10/22/2020

Continual Learning in Low-rank Orthogonal Subspaces

In continual learning (CL), a learner is faced with a sequence of tasks,...

Arslan Chaudhry, et al. ∙

research

∙ 10/10/2020

Diagnosing and Preventing Instabilities in Recurrent Video Processing

Recurrent models are becoming a popular choice for video enhancement tas...

Thomas Tanay, et al. ∙

research

∙ 07/08/2020

How benign is benign overfitting?

We investigate two causes for adversarial vulnerability in deep neural n...

Amartya Sanyal, et al. ∙

research

∙ 06/16/2020

Progressive Skeletonization: Trimming more fat from a network at initialization

Recent studies have shown that skeletonization (pruning parameters) of n...

Pau de Jorge, et al. ∙

research

∙ 04/20/2020

A Revised Generative Evaluation of Visual Dialogue

Evaluating Visual Dialogue, the task of answering a sequence of question...

Daniela Massiceti, et al. ∙

research

∙ 02/21/2020

Calibrating Deep Neural Networks using Focal Loss

Miscalibration – a mismatch between a model's confidence and its correct...

Jishnu Mukhoti, et al. ∙

research

∙ 02/19/2020

Using Hindsight to Anchor Past Knowledge in Continual Learning

In continual learning, the learner faces a stream of data whose distribu...

Arslan Chaudhry, et al. ∙

research

∙ 10/18/2019

Mirror Descent View for Neural Network Quantization

Quantizing large Neural Networks (NN) while maintaining the performance ...

Thalaiyasingam Ajanthan, et al. ∙

research

∙ 09/24/2019

Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation

Arnab Ghosh 6:32 PM We propose an interactive GAN-based sketch-to-image ...

Arnab Ghosh, et al. ∙

research

∙ 06/11/2019

Stable Rank Normalization for Improved Generalization in Neural Networks and GANs

Exciting new work on the generalization bounds for neural networks (NN) ...

Amartya Sanyal, et al. ∙

research

∙ 02/27/2019

Continual Learning with Tiny Episodic Memories

Learning with less supervision is a major challenge in artificial intell...

Arslan Chaudhry, et al. ∙

research

∙ 12/16/2018

Visual Dialogue without Vision or Dialogue

We characterise some of the quirks and shortcomings in the exploration o...

Daniela Massiceti, et al. ∙

research

∙ 12/11/2018

Proximal Mean-field for Neural Network Quantization

Compressing large neural networks by quantizing the parameters, while ma...

Thalaiyasingam Ajanthan, et al. ∙

research

∙ 09/24/2018

Weakly-Supervised Learning of Metric Aggregations for Deformable Image Registration

Deformable registration has been one of the pillars of biomedical image ...

Enzo Ferrante, et al. ∙

research

∙ 01/30/2018

Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence

We study the incremental learning problem for the classification task, a...

Arslan Chaudhry, et al. ∙

research

∙ 07/19/2017

Deformable Registration through Learning of Context-Specific Metric Aggregation

We propose a novel weakly supervised discriminative algorithm for learni...

Enzo Ferrante, et al. ∙

research

∙ 07/18/2017

Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation

We propose an approach to discover class-specific pixels for the weakly-...

Arslan Chaudhry, et al. ∙

research

∙ 04/10/2017

Multi-Agent Diverse Generative Adversarial Networks

This paper describes an intuitive generalization to the Generative Adver...

Arnab Ghosh, et al. ∙

research

∙ 05/30/2016

Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs

In this paper, we propose several improvements on the block-coordinate F...

Anton Osokin, et al. ∙

research

∙ 07/05/2015

Parsimonious Labeling

We propose a new family of discrete energy minimization problems, which ...

Puneet K. Dokania, et al. ∙

Puneet K. Dokania

Featured Co-authors

Philip H. S. Torr

Yarin Gal

Bernard Ghanem

Simon Lacoste-Julien

Alexei A. Efros

Marcus Rohrbach

Eli Shechtman

Richard Hartley

Aleš Leonardis

Marc'Aurelio Ranzato

Mohamed Elhoseiny

ANCER: Anisotropic Certification via Sample-wise Volume Maximization

No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks

On Batch Normalisation for Approximate Bayesian Inference

Continual Learning in Low-rank Orthogonal Subspaces

Diagnosing and Preventing Instabilities in Recurrent Video Processing

How benign is benign overfitting?

Progressive Skeletonization: Trimming more fat from a network at initialization

A Revised Generative Evaluation of Visual Dialogue

Calibrating Deep Neural Networks using Focal Loss

Using Hindsight to Anchor Past Knowledge in Continual Learning

Mirror Descent View for Neural Network Quantization

Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation

Stable Rank Normalization for Improved Generalization in Neural Networks and GANs

Continual Learning with Tiny Episodic Memories

Visual Dialogue without Vision or Dialogue

Proximal Mean-field for Neural Network Quantization

Weakly-Supervised Learning of Metric Aggregations for Deformable Image Registration

Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence

Deformable Registration through Learning of Context-Specific Metric Aggregation

Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation

Multi-Agent Diverse Generative Adversarial Networks

Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs

Parsimonious Labeling