Search Results for author: Chris Russell

Found 52 papers, 25 papers with code

OxonFair: A Flexible Toolkit for Algorithmic Fairness

1 code implementation30 Jun 2024 Eoin Delaney, Zihao Fu, Sandra Wachter, Brent Mittelstadt, Chris Russell

We present OxonFair, a new open source toolkit for enforcing fairness in binary classification.

Binary Classification Fairness

Resource-constrained Fairness

no code implementations3 Jun 2024 Sofie Goethals, Eoin Delaney, Brent Mittelstadt, Chris Russell

Access to resources strongly constrains the decisions we make.

Fairness

Evaluating the Fairness of Discriminative Foundation Models in Computer Vision

no code implementations18 Oct 2023 Junaid Ali, Matthaeus Kleindessner, Florian Wenzel, Kailash Budhathoki, Volkan Cevher, Chris Russell

We propose a novel taxonomy for bias evaluation of discriminative foundation models, such as Contrastive Language-Pretraining (CLIP), that are used for labeling tasks.

Fairness Image Captioning +2

Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTV

1 code implementation ICCV 2023 Jaime Spencer, Chris Russell, Simon Hadfield, Richard Bowden

Unfortunately, existing approaches limit themselves to the automotive domain, resulting in models incapable of generalizing to complex environments such as natural or indoor settings.

Diversity Monocular Depth Estimation +2

Learning Adaptive Neighborhoods for Graph Neural Networks

no code implementations ICCV 2023 Avishkar Saha, Oscar Mendez, Chris Russell, Richard Bowden

Our module can be readily integrated into existing pipelines involving graph convolution operations, replacing the predetermined or existing adjacency matrix with one that is learned, and optimized, as part of the general objective.

Node Classification Point Cloud Classification +1

Image retrieval outperforms diffusion models on data augmentation

no code implementations20 Apr 2023 Max F. Burg, Florian Wenzel, Dominik Zietlow, Max Horn, Osama Makansi, Francesco Locatello, Chris Russell

Many approaches have been proposed to use diffusion models to augment training datasets for downstream tasks, such as classification.

Data Augmentation Image Retrieval +2

Novel View Synthesis of Humans using Differentiable Rendering

1 code implementation28 Mar 2023 Guillaume Rochette, Chris Russell, Richard Bowden

We show how our approach can be used for motion transfer between individuals; novel view synthesis of individuals captured from just a single camera; to synthesize individuals from any virtual viewpoint; and to re-render people in novel poses.

Decoder Image Reconstruction +1

Efficient fair PCA for fair representation learning

1 code implementation26 Feb 2023 Matthäus Kleindessner, Michele Donini, Chris Russell, Muhammad Bilal Zafar

We revisit the problem of fair principal component analysis (PCA), where the goal is to learn the best low-rank linear approximation of the data that obfuscates demographic information.

Representation Learning

The Unfairness of Fair Machine Learning: Levelling down and strict egalitarianism by default

no code implementations5 Feb 2023 Brent Mittelstadt, Sandra Wachter, Chris Russell

Many current fairness measures suffer from both fairness and performance degradation, or "levelling down," where fairness is achieved by making every group worse off, or by bringing better performing groups down to the level of the worst off.

Fairness Jurisprudence

Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that Matter

2 code implementations2 Aug 2022 Jaime Spencer, Chris Russell, Simon Hadfield, Richard Bowden

It is likely that many papers were not only optimized for particular datasets, but also for errors in the data and evaluation criteria.

Monocular Depth Estimation Monocular Reconstruction

Assaying Out-Of-Distribution Generalization in Transfer Learning

1 code implementation19 Jul 2022 Florian Wenzel, Andrea Dittadi, Peter Vincent Gehler, Carl-Johann Simon-Gabriel, Max Horn, Dominik Zietlow, David Kernert, Chris Russell, Thomas Brox, Bernt Schiele, Bernhard Schölkopf, Francesco Locatello

Since out-of-distribution generalization is a generally ill-posed problem, various proxy targets (e. g., calibration, adversarial robustness, algorithmic corruptions, invariance across shifts) were studied across different research programs resulting in different recommendations.

Adversarial Robustness Out-of-Distribution Generalization +1

Pixel-level Correspondence for Self-Supervised Learning from Video

no code implementations8 Jul 2022 Yash Sharma, Yi Zhu, Chris Russell, Thomas Brox

While self-supervised learning has enabled effective representation learning in the absence of labels, for vision, video remains a relatively untapped source of supervision.

Contrastive Learning Image Classification +4

Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks

1 code implementation9 Apr 2022 Michael Lohaus, Matthäus Kleindessner, Krishnaram Kenthapadi, Francesco Locatello, Chris Russell

Based on this observation, we investigate an alternative fairness approach: we add a second classification head to the network to explicitly predict the protected attribute (such as race or gender) alongside the original task.

Attribute Fairness

"The Pedestrian next to the Lamppost" Adaptive Object Graphs for Better Instantaneous Mapping

no code implementations CVPR 2022 Avishkar Saha, Oscar Mendez, Chris Russell, Richard Bowden

Estimating a semantically segmented bird's-eye-view (BEV) map from a single image has become a popular technique for autonomous control and navigation.

Graph Neural Network

Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers

no code implementations CVPR 2022 Dominik Zietlow, Michael Lohaus, Guha Balakrishnan, Matthäus Kleindessner, Francesco Locatello, Bernhard Schölkopf, Chris Russell

Algorithmic fairness is frequently motivated in terms of a trade-off in which overall performance is decreased so as to improve performance on disadvantaged groups where the algorithm would otherwise be less accurate.

Fairness

Human Pose Manipulation and Novel View Synthesis using Differentiable Rendering

1 code implementation24 Nov 2021 Guillaume Rochette, Chris Russell, Richard Bowden

We show how our approach can be used for motion transfer between individuals; novel view synthesis of individuals captured from just a single camera; to synthesize individuals from any virtual viewpoint; and to re-render people in novel poses.

Decoder Image Reconstruction +1

Translating Images into Maps

1 code implementation3 Oct 2021 Avishkar Saha, Oscar Mendez Maldonado, Chris Russell, Richard Bowden

We show how a novel form of transformer network can be used to map from images and video directly to an overhead map or bird's-eye-view (BEV) of the world, in a single end-to-end network.

Translation

Visual Representation Learning Does Not Generalize Strongly Within the Same Domain

1 code implementation ICLR 2022 Lukas Schott, Julius von Kügelgen, Frederik Träuble, Peter Gehler, Chris Russell, Matthias Bethge, Bernhard Schölkopf, Francesco Locatello, Wieland Brendel

An important component for generalization in machine learning is to uncover underlying latent factors of variation as well as the mechanism through which each factor acts in the world.

Representation Learning

Active Sampling for Min-Max Fairness

1 code implementation11 Jun 2020 Jacob Abernethy, Pranjal Awasthi, Matthäus Kleindessner, Jamie Morgenstern, Chris Russell, Jie Zhang

We propose simple active sampling and reweighting strategies for optimizing min-max fairness that can be applied to any classification or regression model learned via loss minimization.

Fairness regression

Why Fairness Cannot Be Automated: Bridging the Gap Between EU Non-Discrimination Law and AI

1 code implementation12 May 2020 Sandra Wachter, Brent Mittelstadt, Chris Russell

Through this proposal for procedural regularity in the identification and assessment of automated discrimination, we clarify how to build considerations of fairness into automated systems as far as possible while still respecting and enabling the contextual approach to judicial interpretation practiced under EU non-discrimination law.

Fairness

Adequate and fair explanations

no code implementations21 Jan 2020 Nicholas Asher, Soumya Paul, Chris Russell

This partiality makes it possible to hide explicit biases present in the algorithm that may be injurious or unfair. We investigate how easy it is to uncover these biases in providing complete and fair explanations by exploiting the structure of the set of counterfactuals providing a complete local explanation.

counterfactual

Weakly-Supervised 3D Pose Estimation from a Single Image using Multi-View Consistency

no code implementations13 Sep 2019 Guillaume Rochette, Chris Russell, Richard Bowden

We present a novel data-driven regularizer for weakly-supervised learning of 3D human pose estimation that eliminates the drift problem that affects existing approaches.

3D Human Pose Estimation 3D Pose Estimation +2

U4D: Unsupervised 4D Dynamic Scene Understanding

no code implementations ICCV 2019 Armin Mustafa, Chris Russell, Adrian Hilton

We introduce the first approach to solve the challenging problem of unsupervised 4D visual scene understanding for complex dynamic scenes with multiple interacting people from multi-view video.

3D Pose Estimation Instance Segmentation +3

Efficient Search for Diverse Coherent Explanations

1 code implementation2 Jan 2019 Chris Russell

This paper proposes new search algorithms for counterfactual explanations based upon mixed integer programming.

counterfactual

Explaining Explanations in AI

no code implementations4 Nov 2018 Brent Mittelstadt, Chris Russell, Sandra Wachter

Recent work on interpretability in machine learning and AI has focused on the building of simplified models that approximate the true criteria used to make decisions.

BIG-bench Machine Learning Philosophy +1

Take a Look Around: Using Street View and Satellite Images to Estimate House Prices

no code implementations18 Jul 2018 Stephen Law, Brooks Paige, Chris Russell

Not only do few quantitative methods exist that can measure the urban environment, but that the collection of such data is both costly and subjective.

Causal Interventions for Fairness

no code implementations6 Jun 2018 Matt J. Kusner, Chris Russell, Joshua R. Loftus, Ricardo Silva

Most approaches in algorithmic fairness constrain machine learning methods so the resulting predictions satisfy one of several intuitive notions of fairness.

Fairness

Causal Reasoning for Algorithmic Fairness

no code implementations15 May 2018 Joshua R. Loftus, Chris Russell, Matt J. Kusner, Ricardo Silva

In this work, we argue for the importance of causal reasoning in creating fair algorithms for decision making.

Decision Making Fairness

Worst-case Optimal Submodular Extensions for Marginal Estimation

1 code implementation10 Jan 2018 Pankaj Pansari, Chris Russell, M. Pawan Kumar

Submodular extensions of an energy function can be used to efficiently compute approximate marginals via variational inference.

Variational Inference

When Worlds Collide: Integrating Different Counterfactual Assumptions in Fairness

no code implementations NeurIPS 2017 Chris Russell, Matt J. Kusner, Joshua Loftus, Ricardo Silva

In this paper, we show how it is possible to make predictions that are approximately fair with respect to multiple possible causal models at once, thus mitigating the problem of exact causal specification.

counterfactual Counterfactual Inference +1

Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR

5 code implementations1 Nov 2017 Sandra Wachter, Brent Mittelstadt, Chris Russell

We suggest data controllers should offer a particular type of explanation, unconditional counterfactual explanations, to support these three aims.

counterfactual Decision Making

Better Together: Joint Reasoning for Non-rigid 3D Reconstruction with Specularities and Shading

no code implementations4 Aug 2017 Qi Liu-Yin, Rui Yu, Lourdes Agapito, Andrew Fitzgibbon, Chris Russell

We demonstrate the use of shape-from-shading (SfS) to improve both the quality and the robustness of 3D reconstruction of dynamic objects captured by a single camera.

3D Reconstruction Object Tracking

VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning

1 code implementation NeurIPS 2017 Akash Srivastava, Lazar Valkov, Chris Russell, Michael U. Gutmann, Charles Sutton

Deep generative models provide powerful tools for distributions over complicated manifolds, such as those of natural images.

Counterfactual Fairness

3 code implementations NeurIPS 2017 Matt J. Kusner, Joshua R. Loftus, Chris Russell, Ricardo Silva

Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing.

BIG-bench Machine Learning Causal Inference +2

Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image

11 code implementations CVPR 2017 Denis Tome, Chris Russell, Lourdes Agapito

We propose a unified formulation for the problem of 3D human pose estimation from a single raw RGB image that reasons jointly about 2D joint estimation and 3D pose reconstruction to improve both tasks.

3D Pose Estimation Monocular 3D Human Pose Estimation +1

Direct, Dense, and Deformable: Template-Based Non-Rigid 3D Reconstruction From RGB Video

no code implementations ICCV 2015 Rui Yu, Chris Russell, Neill D. F. Campbell, Lourdes Agapito

In contrast, our method makes use of a single RGB video as input; it can capture the deformations of generic shapes; and the depth estimation is dense, per-pixel and direct.

3D Reconstruction Depth Estimation +1

Solving Jigsaw Puzzles with Linear Programming

no code implementations13 Nov 2015 Rui Yu, Chris Russell, Lourdes Agapito

We propose a novel Linear Program (LP) based formula- tion for solving jigsaw puzzles.

Position

Part-Based Modelling of Compound Scenes From Images

no code implementations CVPR 2015 Anton van den Hengel, Chris Russell, Anthony Dick, John Bastian, Daniel Pooley, Lachlan Fleming, Lourdes Agapito

We propose a method to recover the structure of a compound scene from multiple silhouettes.

F-formation Detection: Individuating Free-standing Conversational Groups in Images

no code implementations9 Sep 2014 Francesco Setti, Chris Russell, Chiara Bassetti, Marco Cristani

Then, as a main contribution, we present a brand new method for the automatic detection of groups in still images, which is based on a graph-cuts framework for clustering individuals; in particular we are able to codify in a computational sense the sociological definition of F-formation, that is very useful to encode a group having only proxemic information: position and orientation of people.

Clustering

Learning a Manifold as an Atlas

no code implementations CVPR 2013 Nikolaos Pitelis, Chris Russell, Lourdes Agapito

In this work, we return to the underlying mathematical definition of a manifold and directly characterise learning a manifold as finding an atlas, or a set of overlapping charts, that accurately describe local structure.

3D Reconstruction

Efficient Minimization of Higher Order Submodular Functions using Monotonic Boolean Functions

no code implementations11 Sep 2011 Srikumar Ramalingam, Chris Russell, Lubor Ladicky, Philip H. S. Torr

E +n^4 {\log}^{O(1)} n)$ where $E$ is the time required to evaluate the function and $n$ is the number of variables \cite{Lee2015}.

BIG-bench Machine Learning

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