Search Results for author:
Found 45 papers, 22 papers with code
A data augmentation perspective on diffusion models and retrieval
While we find that personalizing diffusion models towards the target data outperforms simpler prompting strategies, we also show that using the training data of the diffusion model alone, via a simple nearest neighbor retrieval procedure, leads to even stronger downstream performance.
The Second Monocular Depth Estimation Challenge
This paper discusses the results for the second edition of the Monocular Depth Estimation Challenge (MDEC).
Novel View Synthesis of Humans using Differentiable Rendering
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.
Efficient fair PCA for fair representation learning
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.
The Unfairness of Fair Machine Learning: Levelling down and strict egalitarianism by default
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.
Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning
Recent years have seen a surge of interest in learning high-level causal representations from low-level image pairs under interventions.
The Monocular Depth Estimation Challenge
This challenge evaluated the progress of self-supervised monocular depth estimation on the challenging SYNS-Patches dataset.
Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that Matter
It is likely that many papers were not only optimized for particular datasets, but also for errors in the data and evaluation criteria.
Assaying Out-Of-Distribution Generalization in Transfer Learning
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
While self-supervised learning has enabled effective representation learning in the absence of labels, for vision, video remains a relatively untapped source of supervision.
Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks
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.
"The Pedestrian next to the Lamppost" Adaptive Object Graphs for Better Instantaneous Mapping
Estimating a semantically segmented bird's-eye-view (BEV) map from a single image has become a popular technique for autonomous control and navigation.
Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers
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.
Human Pose Manipulation and Novel View Synthesis using Differentiable Rendering
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.
Translating Images into Maps
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.
Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
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.
What Did You Think Would Happen? Explaining Agent Behaviour Through Intended Outcomes
We present a novel form of explanation for Reinforcement Learning, based around the notion of intended outcome.
Active Sampling for Min-Max Fairness
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.
Why Fairness Cannot Be Automated: Bridging the Gap Between EU Non-Discrimination Law and AI
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.
Adequate and fair explanations
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.
Explaining Classifiers using Adversarial Perturbations on the Perceptual Ball
We present a simple regularization of adversarial perturbations based upon the perceptual loss.
Fixing Implicit Derivatives: Trust-Region Based Learning of Continuous Energy Functions
We present a new technique for the learning of continuous energy functions that we refer to as Wibergian Learning.
Weakly-Supervised 3D Pose Estimation from a Single Image using Multi-View Consistency
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.
U4D: Unsupervised 4D Dynamic Scene Understanding
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.
Efficient Search for Diverse Coherent Explanations
This paper proposes new search algorithms for counterfactual explanations based upon mixed integer programming.
Explaining Explanations in AI
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.
Rethinking Pose in 3D: Multi-stage Refinement and Recovery for Markerless Motion Capture
We propose a CNN-based approach for multi-camera markerless motion capture of the human body.
Ranked #169 on
3D Human Pose Estimation
on Human3.6M
Take a Look Around: Using Street View and Satellite Images to Estimate House Prices
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
Most approaches in algorithmic fairness constrain machine learning methods so the resulting predictions satisfy one of several intuitive notions of fairness.
Causal Reasoning for Algorithmic Fairness
In this work, we argue for the importance of causal reasoning in creating fair algorithms for decision making.
Worst-case Optimal Submodular Extensions for Marginal Estimation
Submodular extensions of an energy function can be used to efficiently compute approximate marginals via variational inference.
When Worlds Collide: Integrating Different Counterfactual Assumptions in Fairness
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 Explanations without Opening the Black Box: Automated Decisions and the GDPR
We suggest data controllers should offer a particular type of explanation, unconditional counterfactual explanations, to support these three aims.
Better Together: Joint Reasoning for Non-rigid 3D Reconstruction with Specularities and Shading
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.
VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
Deep generative models provide powerful tools for distributions over complicated manifolds, such as those of natural images.
Counterfactual Fairness
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.
Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
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.
Ranked #20 on
Weakly-supervised 3D Human Pose Estimation
on Human3.6M
Direct, Dense, and Deformable: Template-Based Non-Rigid 3D Reconstruction From RGB Video
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.
Solving Jigsaw Puzzles with Linear Programming
We propose a novel Linear Program (LP) based formula- tion for solving jigsaw puzzles.
Part-Based Modelling of Compound Scenes From Images
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
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.
Learning a Manifold as an Atlas
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.
Looking Beyond the Image: Unsupervised Learning for Object Saliency and Detection
We propose a principled probabilistic formulation of object saliency as a sampling problem.
Efficient Minimization of Higher Order Submodular Functions using Monotonic Boolean Functions
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}.
