Search Results for author: Christopher Pal

Found 62 papers, 28 papers with code

Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation

no code implementations19 May 2022 Vikram Voleti, Alexia Jolicoeur-Martineau, Christopher Pal

We train the model in a manner where we randomly and independently mask all the past frames or all the future frames.

Denoising Video Prediction

Overcoming challenges in leveraging GANs for few-shot data augmentation

no code implementations30 Mar 2022 Christopher Beckham, Issam Laradji, Pau Rodriguez, David Vazquez, Derek Nowrouzezahrai, Christopher Pal

In this paper, we explore the use of GAN-based few-shot data augmentation as a method to improve few-shot classification performance.

Classification Data Augmentation

Does entity abstraction help generative Transformers reason?

no code implementations5 Jan 2022 Nicolas Gontier, Siva Reddy, Christopher Pal

We study the utility of incorporating entity type abstractions into pre-trained Transformers and test these methods on four NLP tasks requiring different forms of logical reasoning: (1) compositional language understanding with text-based relational reasoning (CLUTRR), (2) abductive reasoning (ProofWriter), (3) multi-hop question answering (HotpotQA), and (4) conversational question answering (CoQA).

Conversational Question Answering Multi-hop Question Answering +1

Direct Behavior Specification via Constrained Reinforcement Learning

no code implementations22 Dec 2021 Julien Roy, Roger Girgis, Joshua Romoff, Pierre-Luc Bacon, Christopher Pal

The standard formulation of Reinforcement Learning lacks a practical way of specifying what are admissible and forbidden behaviors.

Continuous Control reinforcement-learning

Learning to Guide and to Be Guided in the Architect-Builder Problem

1 code implementation ICLR 2022 Paul Barde, Tristan Karch, Derek Nowrouzezahrai, Clément Moulin-Frier, Christopher Pal, Pierre-Yves Oudeyer

ABIG results in a low-level, high-frequency, guiding communication protocol that not only enables an architect-builder pair to solve the task at hand, but that can also generalize to unseen tasks.

Imitation Learning

Early-Stopping for Meta-Learning: Estimating Generalization from the Activation Dynamics

no code implementations29 Sep 2021 Simon Guiroy, Christopher Pal, Sarath Chandar

To this end, we empirically show that as meta-training progresses, a model's generalization to a target distribution of novel tasks can be estimated by analysing the dynamics of its neural activations.

Few-Shot Learning Transfer Learning

Simple Video Generation using Neural ODEs

no code implementations7 Sep 2021 David Kanaa, Vikram Voleti, Samira Ebrahimi Kahou, Christopher Pal

Despite having been studied to a great extent, the task of conditional generation of sequences of frames, or videos, remains extremely challenging.

Frame Video Generation

Multi-Resolution Continuous Normalizing Flows

1 code implementation15 Jun 2021 Vikram Voleti, Chris Finlay, Adam Oberman, Christopher Pal

In this work we introduce a Multi-Resolution variant of such models (MRCNF), by characterizing the conditional distribution over the additional information required to generate a fine image that is consistent with the coarse image.

 Ranked #1 on Image Generation on ImageNet 128x128 (bpd metric)

Density Estimation Image Generation

Beyond Target Networks: Improving Deep $Q$-learning with Functional Regularization

no code implementations4 Jun 2021 Alexandre Piché, Valentin Thomas, Joseph Marino, Gian Maria Marconi, Christopher Pal, Mohammad Emtiyaz Khan

However, training is often unstable due to fast-changing target Q-values, and target networks are employed to regularize the Q-value estimation and stabilize training by using an additional set of lagging parameters.

Q-Learning

Improving Continuous Normalizing Flows using a Multi-Resolution Framework

no code implementations ICML Workshop INNF 2021 Vikram Voleti, Chris Finlay, Adam M Oberman, Christopher Pal

Recent work has shown that Continuous Normalizing Flows (CNFs) can serve as generative models of images with exact likelihood calculation and invertible generation/density estimation.

Density Estimation

Robust Motion In-betweening

1 code implementation9 Feb 2021 Félix G. Harvey, Mike Yurick, Derek Nowrouzezahrai, Christopher Pal

To quantitatively evaluate performance on transitions and generalizations to longer time horizons, we present well-defined in-betweening benchmarks on a subset of the widely used Human3. 6M dataset and on LaFAN1, a novel high quality motion capture dataset that is more appropriate for transition generation.

Human Pose Forecasting motion prediction +1

Visual Question Answering From Another Perspective: CLEVR Mental Rotation Tests

no code implementations1 Jan 2021 Christopher Beckham, Martin Weiss, Florian Golemo, Sina Honari, Derek Nowrouzezahrai, Christopher Pal

To do this we have created a new version of the CLEVR VQA problem setup and dataset that we call CLEVR Mental Rotation Tests or CLEVR-MRT, where the goal is to answer questions about the original CLEVR viewpoint given a single image obtained from a different viewpoint of the same scene.

3D Reconstruction Contrastive Learning +4

Dependency Structure Discovery from Interventions

no code implementations1 Jan 2021 Nan Rosemary Ke, Olexa Bilaniuk, Anirudh Goyal, Stefan Bauer, Bernhard Schölkopf, Michael Curtis Mozer, Hugo Larochelle, Christopher Pal, Yoshua Bengio

Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data.

Mem2Mem: Learning to Summarize Long Texts with Memory Compression and Transfer

no code implementations1 Jan 2021 Jonathan Pilault, Jaehong Park, Christopher Pal

We introduce Mem2Mem, a memory-to-memory mechanism for hierarchical recurrent neural network based encoder decoder architectures and we explore its use for abstractive document summarization.

Abstractive Text Summarization Document Summarization

Visual Imitation with Reinforcement Learning using Recurrent Siamese Networks

no code implementations1 Jan 2021 Glen Berseth, Florian Golemo, Christopher Pal

It would be desirable for a reinforcement learning (RL) based agent to learn behaviour by merely watching a demonstration.

One-Shot Learning reinforcement-learning

Bijective-Contrastive Estimation

no code implementations pproximateinference AABI Symposium 2021 Jae Hyun Lim, Chin-wei Huang, Aaron Courville, Christopher Pal

In this work, we propose Bijective-Contrastive Estimation (BCE), a classification-based learning criterion for energy-based models.

Classification

Learning to Summarize Long Texts with Memory Compression and Transfer

no code implementations21 Oct 2020 Jaehong Park, Jonathan Pilault, Christopher Pal

We introduce Mem2Mem, a memory-to-memory mechanism for hierarchical recurrent neural network based encoder decoder architectures and we explore its use for abstractive document summarization.

Abstractive Text Summarization Document Summarization

Reinforcement Learning with Random Delays

1 code implementation ICLR 2021 Simon Ramstedt, Yann Bouteiller, Giovanni Beltrame, Christopher Pal, Jonathan Binas

Action and observation delays commonly occur in many Reinforcement Learning applications, such as remote control scenarios.

Continuous Control reinforcement-learning

Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data

1 code implementation ICLR 2021 Jonathan Pilault, Amine Elhattami, Christopher Pal

Through this construction (a hypernetwork adapter), we achieve more efficient parameter sharing and mitigate forgetting by keeping half of the weights of a pretrained model fixed.

Multi-Task Learning Natural Language Inference

Action-Based Representation Learning for Autonomous Driving

1 code implementation21 Aug 2020 Yi Xiao, Felipe Codevilla, Christopher Pal, Antonio M. Lopez

Human drivers produce a vast amount of data which could, in principle, be used to improve autonomous driving systems.

Autonomous Driving Representation Learning

Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization

3 code implementations NeurIPS 2020 Paul Barde, Julien Roy, Wonseok Jeon, Joelle Pineau, Christopher Pal, Derek Nowrouzezahrai

Adversarial Imitation Learning alternates between learning a discriminator -- which tells apart expert's demonstrations from generated ones -- and a generator's policy to produce trajectories that can fool this discriminator.

Imitation Learning reinforcement-learning

AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation

2 code implementations ICML 2020 Jae Hyun Lim, Aaron Courville, Christopher Pal, Chin-wei Huang

Entropy is ubiquitous in machine learning, but it is in general intractable to compute the entropy of the distribution of an arbitrary continuous random variable.

Continuous Control Denoising +1

On the impressive performance of randomly weighted encoders in summarization tasks

no code implementations21 Feb 2020 Jonathan Pilault, Jae-hong Park, Christopher Pal

In this work, we investigate the performance of untrained randomly initialized encoders in a general class of sequence to sequence models and compare their performance with that of fully-trained encoders on the task of abstractive summarization.

Abstractive Text Summarization

Structural Inductive Biases in Emergent Communication

no code implementations4 Feb 2020 Agnieszka Słowik, Abhinav Gupta, William L. Hamilton, Mateja Jamnik, Sean B. Holden, Christopher Pal

In order to communicate, humans flatten a complex representation of ideas and their attributes into a single word or a sentence.

Representation Learning

Real-Time Reinforcement Learning

3 code implementations NeurIPS 2019 Simon Ramstedt, Christopher Pal

Markov Decision Processes (MDPs), the mathematical framework underlying most algorithms in Reinforcement Learning (RL), are often used in a way that wrongfully assumes that the state of an agent's environment does not change during action selection.

Continuous Control reinforcement-learning

Neural Multisensory Scene Inference

2 code implementations NeurIPS 2019 Jae Hyun Lim, Pedro O. Pinheiro, Negar Rostamzadeh, Christopher Pal, Sungjin Ahn

For embodied agents to infer representations of the underlying 3D physical world they inhabit, they should efficiently combine multisensory cues from numerous trials, e. g., by looking at and touching objects.

Representation Learning

Interactive Machine Comprehension with Information Seeking Agents

1 code implementation ACL 2020 Xingdi Yuan, Jie Fu, Marc-Alexandre Cote, Yi Tay, Christopher Pal, Adam Trischler

Existing machine reading comprehension (MRC) models do not scale effectively to real-world applications like web-level information retrieval and question answering (QA).

Decision Making Information Retrieval +2

Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning

no code implementations NeurIPS 2020 Julien Roy, Paul Barde, Félix G. Harvey, Derek Nowrouzezahrai, Christopher Pal

Finally, we analyze the effects of our proposed methods on the policies that our agents learn and show that our methods successfully enforce the qualities that we propose as proxies for coordinated behaviors.

Continuous Control Multi-agent Reinforcement Learning +1

Towards Understanding Generalization in Gradient-Based Meta-Learning

no code implementations16 Jul 2019 Simon Guiroy, Vikas Verma, Christopher Pal

We also show that coherence of meta-test gradients, measured by the average inner product between the task-specific gradient vectors evaluated at meta-train solution, is also correlated with generalization.

Meta-Learning

Supervise Thyself: Examining Self-Supervised Representations in Interactive Environments

2 code implementations27 Jun 2019 Evan Racah, Christopher Pal

Self-supervised methods, wherein an agent learns representations solely by observing the results of its actions, become crucial in environments which do not provide a dense reward signal or have labels.

Imitation Learning

Adversarial Mixup Resynthesizers

no code implementations ICLR Workshop DeepGenStruct 2019 Christopher Beckham, Sina Honari, Alex Lamb, Vikas Verma, Farnoosh Ghadiri, R Devon Hjelm, Christopher Pal

In this paper, we explore new approaches to combining information encoded within the learned representations of autoencoders.

On Adversarial Mixup Resynthesis

1 code implementation NeurIPS 2019 Christopher Beckham, Sina Honari, Vikas Verma, Alex Lamb, Farnoosh Ghadiri, R. Devon Hjelm, Yoshua Bengio, Christopher Pal

In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders.

Resynthesis

Towards Learning to Imitate from a Single Video Demonstration

no code implementations22 Jan 2019 Glen Berseth, Florian Golemo, Christopher Pal

We approach this challenge using contrastive training to learn a reward function comparing an agent's behaviour with a single demonstration.

Imitation Learning One-Shot Learning

Dataflow-based Joint Quantization of Weights and Activations for Deep Neural Networks

no code implementations4 Jan 2019 Xue Geng, Jie Fu, Bin Zhao, Jie Lin, Mohamed M. Sabry Aly, Christopher Pal, Vijay Chandrasekhar

This paper addresses a challenging problem - how to reduce energy consumption without incurring performance drop when deploying deep neural networks (DNNs) at the inference stage.

Quantization

Recurrent Transition Networks for Character Locomotion

2 code implementations4 Oct 2018 Félix G. Harvey, Christopher Pal

Manually authoring transition animations for a complete locomotion system can be a tedious and time-consuming task, especially for large games that allow complex and constrained locomotion movements, where the number of transitions grows exponentially with the number of states.

Super-Resolution

Unsupervised Depth Estimation, 3D Face Rotation and Replacement

1 code implementation NeurIPS 2018 Joel Ruben Antony Moniz, Christopher Beckham, Simon Rajotte, Sina Honari, Christopher Pal

We present an unsupervised approach for learning to estimate three dimensional (3D) facial structure from a single image while also predicting 3D viewpoint transformations that match a desired pose and facial geometry.

Depth Estimation Translation

Improving Landmark Localization with Semi-Supervised Learning

no code implementations CVPR 2018 Sina Honari, Pavlo Molchanov, Stephen Tyree, Pascal Vincent, Christopher Pal, Jan Kautz

First, we propose the framework of sequential multitasking and explore it here through an architecture for landmark localization where training with class labels acts as an auxiliary signal to guide the landmark localization on unlabeled data.

Small Data Image Classification

A step towards procedural terrain generation with GANs

no code implementations11 Jul 2017 Christopher Beckham, Christopher Pal

Procedural terrain generation for video games has been traditionally been done with smartly designed but handcrafted algorithms that generate heightmaps.

Adversarial Generation of Natural Language

no code implementations WS 2017 Sai Rajeswar, Sandeep Subramanian, Francis Dutil, Christopher Pal, Aaron Courville

Generative Adversarial Networks (GANs) have gathered a lot of attention from the computer vision community, yielding impressive results for image generation.

Image Generation Language Modelling

Unimodal probability distributions for deep ordinal classification

no code implementations ICML 2017 Christopher Beckham, Christopher Pal

Probability distributions produced by the cross-entropy loss for ordinal classification problems can possess undesired properties.

Classification General Classification

ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events

1 code implementation NeurIPS 2017 Evan Racah, Christopher Beckham, Tegan Maharaj, Samira Ebrahimi Kahou, Prabhat, Christopher Pal

We present a dataset, ExtremeWeather, to encourage machine learning research in this area and to help facilitate further work in understanding and mitigating the effects of climate change.

A simple squared-error reformulation for ordinal classification

1 code implementation2 Dec 2016 Christopher Beckham, Christopher Pal

In this paper, we explore ordinal classification (in the context of deep neural networks) through a simple modification of the squared error loss which not only allows it to not only be sensitive to class ordering, but also allows the possibility of having a discrete probability distribution over the classes.

Classification General Classification

A dataset and exploration of models for understanding video data through fill-in-the-blank question-answering

2 code implementations CVPR 2017 Tegan Maharaj, Nicolas Ballas, Anna Rohrbach, Aaron Courville, Christopher Pal

In addition to presenting statistics and a description of the dataset, we perform a detailed analysis of 5 different models' predictions, and compare these with human performance.

Language Modelling Object Detection +1

Convolutional Residual Memory Networks

no code implementations16 Jun 2016 Joel Moniz, Christopher Pal

Our experiments and analysis explore the importance of the memory mechanism, network depth, breadth, and predictive performance.

Movie Description

no code implementations12 May 2016 Anna Rohrbach, Atousa Torabi, Marcus Rohrbach, Niket Tandon, Christopher Pal, Hugo Larochelle, Aaron Courville, Bernt Schiele

In addition we also collected and aligned movie scripts used in prior work and compare the two sources of descriptions.

Theano: A Python framework for fast computation of mathematical expressions

1 code implementation9 May 2016 The Theano Development Team, Rami Al-Rfou, Guillaume Alain, Amjad Almahairi, Christof Angermueller, Dzmitry Bahdanau, Nicolas Ballas, Frédéric Bastien, Justin Bayer, Anatoly Belikov, Alexander Belopolsky, Yoshua Bengio, Arnaud Bergeron, James Bergstra, Valentin Bisson, Josh Bleecher Snyder, Nicolas Bouchard, Nicolas Boulanger-Lewandowski, Xavier Bouthillier, Alexandre de Brébisson, Olivier Breuleux, Pierre-Luc Carrier, Kyunghyun Cho, Jan Chorowski, Paul Christiano, Tim Cooijmans, Marc-Alexandre Côté, Myriam Côté, Aaron Courville, Yann N. Dauphin, Olivier Delalleau, Julien Demouth, Guillaume Desjardins, Sander Dieleman, Laurent Dinh, Mélanie Ducoffe, Vincent Dumoulin, Samira Ebrahimi Kahou, Dumitru Erhan, Ziye Fan, Orhan Firat, Mathieu Germain, Xavier Glorot, Ian Goodfellow, Matt Graham, Caglar Gulcehre, Philippe Hamel, Iban Harlouchet, Jean-Philippe Heng, Balázs Hidasi, Sina Honari, Arjun Jain, Sébastien Jean, Kai Jia, Mikhail Korobov, Vivek Kulkarni, Alex Lamb, Pascal Lamblin, Eric Larsen, César Laurent, Sean Lee, Simon Lefrancois, Simon Lemieux, Nicholas Léonard, Zhouhan Lin, Jesse A. Livezey, Cory Lorenz, Jeremiah Lowin, Qianli Ma, Pierre-Antoine Manzagol, Olivier Mastropietro, Robert T. McGibbon, Roland Memisevic, Bart van Merriënboer, Vincent Michalski, Mehdi Mirza, Alberto Orlandi, Christopher Pal, Razvan Pascanu, Mohammad Pezeshki, Colin Raffel, Daniel Renshaw, Matthew Rocklin, Adriana Romero, Markus Roth, Peter Sadowski, John Salvatier, François Savard, Jan Schlüter, John Schulman, Gabriel Schwartz, Iulian Vlad Serban, Dmitriy Serdyuk, Samira Shabanian, Étienne Simon, Sigurd Spieckermann, S. Ramana Subramanyam, Jakub Sygnowski, Jérémie Tanguay, Gijs van Tulder, Joseph Turian, Sebastian Urban, Pascal Vincent, Francesco Visin, Harm de Vries, David Warde-Farley, Dustin J. Webb, Matthew Willson, Kelvin Xu, Lijun Xue, Li Yao, Saizheng Zhang, Ying Zhang

Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements.

Dimensionality Reduction General Classification

Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation

1 code implementation CVPR 2016 Sina Honari, Jason Yosinski, Pascal Vincent, Christopher Pal

Deep neural networks with alternating convolutional, max-pooling and decimation layers are widely used in state of the art architectures for computer vision.

Image Classification

Recurrent Semi-supervised Classification and Constrained Adversarial Generation with Motion Capture Data

no code implementations20 Nov 2015 Félix G. Harvey, Julien Roy, David Kanaa, Christopher Pal

We find that using such constraints allow to stabilize the training of recurrent adversarial architectures for animation generation.

General Classification

Describing Videos by Exploiting Temporal Structure

5 code implementations ICCV 2015 Li Yao, Atousa Torabi, Kyunghyun Cho, Nicolas Ballas, Christopher Pal, Hugo Larochelle, Aaron Courville

In this context, we propose an approach that successfully takes into account both the local and global temporal structure of videos to produce descriptions.

Action Recognition Video Description

Cannot find the paper you are looking for? You can Submit a new open access paper.