Search Results for author: Liam Paull

Found 40 papers, 16 papers with code

BACS: Background Aware Continual Semantic Segmentation

1 code implementation19 Apr 2024 Mostafa ElAraby, Ali Harakeh, Liam Paull

Besides the common problem of classical catastrophic forgetting in the continual learning setting, CSS suffers from the inherent ambiguity of the background, a phenomenon we refer to as the "background shift'', since pixels labeled as background could correspond to future classes (forward background shift) or previous classes (backward background shift).

Autonomous Driving Continual Learning +5

Rethinking Teacher-Student Curriculum Learning through the Cooperative Mechanics of Experience

no code implementations3 Apr 2024 Manfred Diaz, Liam Paull, Andrea Tacchetti

Teacher-Student Curriculum Learning (TSCL) is a curriculum learning framework that draws inspiration from human cultural transmission and learning.

CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learning

no code implementations29 Mar 2024 Luke Rowe, Roger Girgis, Anthony Gosselin, Bruno Carrez, Florian Golemo, Felix Heide, Liam Paull, Christopher Pal

With this dataset, we train a return-conditioned multi-agent behaviour model that allows for fine-grained manipulation of agent behaviours by modifying the desired returns for the various reward components.


Ghost on the Shell: An Expressive Representation of General 3D Shapes

no code implementations23 Oct 2023 Zhen Liu, Yao Feng, Yuliang Xiu, Weiyang Liu, Liam Paull, Michael J. Black, Bernhard Schölkopf

Recent work has focused on the former, and methods for reconstructing open surfaces do not support fast reconstruction with material and lighting or unconditional generative modelling.

ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning

no code implementations28 Sep 2023 Qiao Gu, Alihusein Kuwajerwala, Sacha Morin, Krishna Murthy Jatavallabhula, Bipasha Sen, Aditya Agarwal, Corban Rivera, William Paul, Kirsty Ellis, Rama Chellappa, Chuang Gan, Celso Miguel de Melo, Joshua B. Tenenbaum, Antonio Torralba, Florian Shkurti, Liam Paull

We demonstrate the utility of this representation through a number of downstream planning tasks that are specified through abstract (language) prompts and require complex reasoning over spatial and semantic concepts.

MeshDiffusion: Score-based Generative 3D Mesh Modeling

1 code implementation14 Mar 2023 Zhen Liu, Yao Feng, Michael J. Black, Derek Nowrouzezahrai, Liam Paull, Weiyang Liu

We consider the task of generating realistic 3D shapes, which is useful for a variety of applications such as automatic scene generation and physical simulation.

Scene Generation

ConceptFusion: Open-set Multimodal 3D Mapping

1 code implementation14 Feb 2023 Krishna Murthy Jatavallabhula, Alihusein Kuwajerwala, Qiao Gu, Mohd Omama, Tao Chen, Alaa Maalouf, Shuang Li, Ganesh Iyer, Soroush Saryazdi, Nikhil Keetha, Ayush Tewari, Joshua B. Tenenbaum, Celso Miguel de Melo, Madhava Krishna, Liam Paull, Florian Shkurti, Antonio Torralba

ConceptFusion leverages the open-set capabilities of today's foundation models pre-trained on internet-scale data to reason about concepts across modalities such as natural language, images, and audio.

Autonomous Driving Robot Navigation

Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss

no code implementations CVPR 2023 Anas Mahmoud, Jordan S. K. Hu, Tianshu Kuai, Ali Harakeh, Liam Paull, Steven L. Waslander

However, image-to point representation learning for autonomous driving datasets faces two main challenges: 1) the abundance of self-similarity, which results in the contrastive losses pushing away semantically similar point and image regions and thus disturbing the local semantic structure of the learned representations, and 2) severe class imbalance as pretraining gets dominated by over-represented classes.

3D Semantic Segmentation Autonomous Driving +4

Multi-Agent Reinforcement Learning for Fast-Timescale Demand Response of Residential Loads

no code implementations6 Jan 2023 Vincent Mai, Philippe Maisonneuve, Tianyu Zhang, Hadi Nekoei, Liam Paull, Antoine Lesage-Landry

To integrate high amounts of renewable energy resources, electrical power grids must be able to cope with high amplitude, fast timescale variations in power generation.

Multi-agent Reinforcement Learning reinforcement-learning +1

Estimating Regression Predictive Distributions with Sample Networks

no code implementations24 Nov 2022 Ali Harakeh, Jordan Hu, Naiqing Guan, Steven L. Waslander, Liam Paull

A common approach to model uncertainty is to choose a parametric distribution and fit the data to it using maximum likelihood estimation.


NeurIPS 2022 Competition: Driving SMARTS

no code implementations14 Nov 2022 Amir Rasouli, Randy Goebel, Matthew E. Taylor, Iuliia Kotseruba, Soheil Alizadeh, Tianpei Yang, Montgomery Alban, Florian Shkurti, Yuzheng Zhuang, Adam Scibior, Kasra Rezaee, Animesh Garg, David Meger, Jun Luo, Liam Paull, Weinan Zhang, Xinyu Wang, Xi Chen

The proposed competition supports methodologically diverse solutions, such as reinforcement learning (RL) and offline learning methods, trained on a combination of naturalistic AD data and open-source simulation platform SMARTS.

Autonomous Driving Reinforcement Learning (RL)

Structural Causal 3D Reconstruction

no code implementations20 Jul 2022 Weiyang Liu, Zhen Liu, Liam Paull, Adrian Weller, Bernhard Schölkopf

This paper considers the problem of unsupervised 3D object reconstruction from in-the-wild single-view images.

3D Object Reconstruction 3D Reconstruction +2

Monocular Robot Navigation with Self-Supervised Pretrained Vision Transformers

no code implementations7 Mar 2022 Miguel Saavedra-Ruiz, Sacha Morin, Liam Paull

In this work, we consider the problem of learning a perception model for monocular robot navigation using few annotated images.

Image Segmentation Robot Navigation +2

Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation

1 code implementation ICLR 2022 Vincent Mai, Kaustubh Mani, Liam Paull

In model-free deep reinforcement learning (RL) algorithms, using noisy value estimates to supervise policy evaluation and optimization is detrimental to the sample efficiency.

Continuous Control reinforcement-learning +1

Iterative Teaching by Label Synthesis

no code implementations NeurIPS 2021 Weiyang Liu, Zhen Liu, Hanchen Wang, Liam Paull, Bernhard Schölkopf, Adrian Weller

In this paper, we consider the problem of iterative machine teaching, where a teacher provides examples sequentially based on the current iterative learner.

Lifelong Topological Visual Navigation

no code implementations16 Oct 2021 Rey Reza Wiyatno, Anqi Xu, Liam Paull

Commonly, learning-based topological navigation approaches produce a local policy while preserving some loose connectivity of the space through a topological map.

Visual Navigation

On Assessing the Usefulness of Proxy Domains for Developing and Evaluating Embodied Agents

1 code implementation29 Sep 2021 Anthony Courchesne, Andrea Censi, Liam Paull

We propose the relative predictive PU to assess the predictive ability of a proxy domain and the learning PU to quantify the usefulness of a proxy as a tool to generate learning data.

$f$-Cal: Calibrated aleatoric uncertainty estimation from neural networks for robot perception

no code implementations28 Sep 2021 Dhaivat Bhatt, Kaustubh Mani, Dishank Bansal, Krishna Murthy, Hanju Lee, Liam Paull

While modern deep neural networks are performant perception modules, performance (accuracy) alone is insufficient, particularly for safety-critical robotic applications such as self-driving vehicles.

Monocular Depth Estimation object-detection +1

Batch Inverse-Variance Weighting: Deep Heteroscedastic Regression

no code implementations9 Jul 2021 Vincent Mai, Waleed Khamies, Liam Paull

In many situations however, the labelling process is able to estimate the variance of such distribution for each label, which can be used as an additional information to mitigate this impact.


Batch Inverse-Variance Weighting: Deep Heteroscedastic Regression using Privileged Information

no code implementations1 Jan 2021 Vincent Mai, Waleed Khamies, Liam Paull

In this work, we consider this setting and additionally assume that the label generating process is able to provide us with a quantity for the role of each label in the misalignment between the datasets, which we consider to be privileged information.


Look-ahead Meta Learning for Continual Learning

2 code implementations NeurIPS 2020 Gunshi Gupta, Karmesh Yadav, Liam Paull

The continual learning problem involves training models with limited capacity to perform well on a set of an unknown number of sequentially arriving tasks.

Continual Learning Meta-Learning

La-MAML: Look-ahead Meta Learning for Continual Learning

3 code implementations ICML Workshop LifelongML 2020 Gunshi Gupta, Karmesh Yadav, Liam Paull

The continual learning problem involves training models with limited capacity to perform well on a set of an unknown number of sequentially arriving tasks.

Continual Learning Meta-Learning

Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling

3 code implementations NeurIPS 2020 Tong Che, Ruixiang Zhang, Jascha Sohl-Dickstein, Hugo Larochelle, Liam Paull, Yuan Cao, Yoshua Bengio

To make that practical, we show that sampling from this modified density can be achieved by sampling in latent space according to an energy-based model induced by the sum of the latent prior log-density and the discriminator output score.

Image Generation

Curriculum in Gradient-Based Meta-Reinforcement Learning

no code implementations19 Feb 2020 Bhairav Mehta, Tristan Deleu, Sharath Chandra Raparthy, Chris J. Pal, Liam Paull

However, specifically in the case of meta-reinforcement learning (meta-RL), we can show that gradient-based meta-learners are sensitive to task distributions.

Benchmarking Meta-Learning +4

Generating Automatic Curricula via Self-Supervised Active Domain Randomization

1 code implementation18 Feb 2020 Sharath Chandra Raparthy, Bhairav Mehta, Florian Golemo, Liam Paull

Goal-directed Reinforcement Learning (RL) traditionally considers an agent interacting with an environment, prescribing a real-valued reward to an agent proportional to the completion of some goal.

Reinforcement Learning (RL)

gradSLAM: Automagically differentiable SLAM

1 code implementation23 Oct 2019 Krishna Murthy Jatavallabhula, Soroush Saryazdi, Ganesh Iyer, Liam Paull

Blending representation learning approaches with simultaneous localization and mapping (SLAM) systems is an open question, because of their highly modular and complex nature.

Open-Ended Question Answering Representation Learning +1

Perceptual Generative Autoencoders

2 code implementations ICML 2020 Zijun Zhang, Ruixiang Zhang, Zongpeng Li, Yoshua Bengio, Liam Paull

We therefore propose to map both the generated and target distributions to a latent space using the encoder of a standard autoencoder, and train the generator (or decoder) to match the target distribution in the latent space.


Active Domain Randomization

2 code implementations9 Apr 2019 Bhairav Mehta, Manfred Diaz, Florian Golemo, Christopher J. Pal, Liam Paull

Our experiments show that domain randomization may lead to suboptimal, high-variance policies, which we attribute to the uniform sampling of environment parameters.


Deep Active Localization

1 code implementation5 Mar 2019 Sai Krishna, Keehong Seo, Dhaivat Bhatt, Vincent Mai, Krishna Murthy, Liam Paull

Traditional approaches to this use an information-theoretic criterion for action selection and hand-crafted perceptual models.

OpenAI Gym

A Data-Efficient Framework for Training and Sim-to-Real Transfer of Navigation Policies

no code implementations11 Oct 2018 Homanga Bharadhwaj, Zihan Wang, Yoshua Bengio, Liam Paull

Learning effective visuomotor policies for robots purely from data is challenging, but also appealing since a learning-based system should not require manual tuning or calibration.


Geometric Consistency for Self-Supervised End-to-End Visual Odometry

no code implementations11 Apr 2018 Ganesh Iyer, J. Krishna Murthy, Gunshi Gupta, K. Madhava Krishna, Liam Paull

We show that using a noisy teacher, which could be a standard VO pipeline, and by designing a loss term that enforces geometric consistency of the trajectory, we can train accurate deep models for VO that do not require ground-truth labels.

Visual Odometry

SLAM with Objects using a Nonparametric Pose Graph

2 code implementations19 Apr 2017 Beipeng Mu, Shih-Yuan Liu, Liam Paull, John Leonard, Jonathan How

The \textit{data association} and \textit{simultaneous localization and mapping} (SLAM) problems are, individually, well-studied in the literature.

Simultaneous Localization and Mapping

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