Search Results for author:
Found 22 papers, 6 papers with code
Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & Beyond
Multi-Task Learning (MTL) is a framework, where multiple related tasks are learned jointly and benefit from a shared representation space, or parameter transfer.
Ranked #1 on
Facial Expression Recognition (FER)
on AffectNet
(Accuracy (7 emotion) metric, using extra
training data)
Okapi: Generalising Better by Making Statistical Matches Match
In order to perform the online matching in a runtime- and memory-efficient way, we draw upon the self-supervised literature and combine a memory bank with a slow-moving momentum encoder.
Free-HeadGAN: Neural Talking Head Synthesis with Explicit Gaze Control
We present Free-HeadGAN, a person-generic neural talking head synthesis system.
RealPatch: A Statistical Matching Framework for Model Patching with Real Samples
We demonstrate the effectiveness of RealPatch on three benchmark datasets, CelebA, Waterbirds and a subset of iWildCam, showing improvements in worst-case subgroup performance and in subgroup performance gap in binary classification.
DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image
Experimentally, DAD-3DNet outperforms or is comparable to the state-of-the-art models in (i) 3D Head Pose Estimation on AFLW2000-3D and BIWI, (ii) 3D Face Shape Reconstruction on NoW and Feng, and (iii) 3D Dense Head Alignment and 3D Landmarks Estimation on DAD-3DHeads dataset.
Ranked #6 on
Head Pose Estimation
on AFLW2000
Addressing Missing Sources with Adversarial Support-Matching
We investigate a scenario in which the absence of certain data is linked to the second level of a two-level hierarchy in the data.
Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study
Based on this approach, we build FaceBehaviorNet, the first framework for large-scale face analysis, by jointly learning all facial behavior tasks.
Ranked #5 on
Facial Expression Recognition (FER)
on RAF-DB
(Avg. Accuracy metric, using extra
training data)
Head2HeadFS: Video-based Head Reenactment with Few-shot Learning
Head reenactment is an even more challenging task, which aims at transferring not only the facial expression, but also the entire head pose from a source person to a target.
Zero-shot Fairness with Invisible Demographics
In a statistical notion of algorithmic fairness, we partition individuals into groups based on some key demographic factors such as race and gender, and require that some statistics of a classifier be approximately equalized across those groups.
HeadGAN: One-shot Neural Head Synthesis and Editing
Recent attempts to solve the problem of head reenactment using a single reference image have shown promising results.
Head2Head++: Deep Facial Attributes Re-Targeting
Facial video re-targeting is a challenging problem aiming to modify the facial attributes of a target subject in a seamless manner by a driving monocular sequence.
Contrastive Examples for Addressing the Tyranny of the Majority
Computer vision algorithms, e. g. for face recognition, favour groups of individuals that are better represented in the training data.
Face Behavior a la carte: Expressions, Affect and Action Units in a Single Network
We present the first and the largest study of all facial behaviour tasks learned jointly in a single multi-task, multi-domain and multi-label network, which we call FaceBehaviorNet.
Video-to-Video Translation for Visual Speech Synthesis
Despite remarkable success in image-to-image translation that celebrates the advancements of generative adversarial networks (GANs), very limited attempts are known for video domain translation.
Recycling Privileged Learning and Distribution Matching for Fairness
We set an overarching goal to develop a unified machine learning framework that is able to handle any definitions of fairness, their combinations, and also new definitions that might be stipulated in the future.
Learning From the Mistakes of Others: Matching Errors in Cross-Dataset Learning
Can we learn about object classes in images by looking at a collection of relevant 3D models?
Ambiguity Helps: Classification With Disagreements in Crowdsourced Annotations
On the technical side, we propose a framework to incorporate annotation disagreements into the classifiers.
Curriculum Learning of Multiple Tasks
Sharing information between multiple tasks enables algorithms to achieve good generalization performance even from small amounts of training data.
Learning to Transfer Privileged Information
We interpret these methods as learning easiness and hardness of the objects in the privileged space and then transferring this knowledge to train a better classifier in the original space.
Mind the Nuisance: Gaussian Process Classification using Privileged Noise
That is, in contrast to the standard GPC setting, the latent function is not just a nuisance but a feature: it becomes a natural measure of confidence about the training data by modulating the slope of the GPC sigmoid likelihood function.
The Supervised IBP: Neighbourhood Preserving Infinite Latent Feature Models
We propose a probabilistic model to infer supervised latent variables in the Hamming space from observed data.
