Search Results for author: Nicholas Apostoloff

Found 15 papers, 0 papers with code

On the role of Lip Articulation in Visual Speech Perception

no code implementations18 Mar 2022 Zakaria Aldeneh, Masha Fedzechkina, Skyler Seto, Katherine Metcalf, Miguel Sarabia, Nicholas Apostoloff, Barry-John Theobald

Previous research has shown that traditional metrics used to optimize and assess models for generating lip motion from speech are not a good indicator of subjective opinion of animation quality.

FedEmbed: Personalized Private Federated Learning

no code implementations18 Feb 2022 Andrew Silva, Katherine Metcalf, Nicholas Apostoloff, Barry-John Theobald

Federated learning enables the deployment of machine learning to problems for which centralized data collection is impractical.

Federated Learning

Fair SA: Sensitivity Analysis for Fairness in Face Recognition

no code implementations8 Feb 2022 Aparna R. Joshi, Xavier Suau, Nivedha Sivakumar, Luca Zappella, Nicholas Apostoloff

One such high impact domain is that of face recognition, with real world applications involving images affected by various degradations, such as motion blur or high exposure.

Face Recognition Fairness

FORML: Learning to Reweight Data for Fairness

no code implementations3 Feb 2022 Bobby Yan, Skyler Seto, Nicholas Apostoloff

Machine learning models are trained to minimize the mean loss for a single metric, and thus typically do not consider fairness and robustness.

Fairness Image Classification +2

Challenges of Adversarial Image Augmentations

no code implementations NeurIPS Workshop ICBINB 2021 Arno Blaas, Xavier Suau, Jason Ramapuram, Nicholas Apostoloff, Luca Zappella

Image augmentations applied during training are crucial for the generalization performance of image classifiers.

Self-conditioning pre-trained language models

no code implementations30 Sep 2021 Xavier Suau, Luca Zappella, Nicholas Apostoloff

We compare our method with FUDGE and PPLM-BoW, and show that our approach is able to achieve gender parity at a lower perplexity.

Text Generation

MorphGAN: One-Shot Face Synthesis GAN for Detecting Recognition Bias

no code implementations9 Dec 2020 Nataniel Ruiz, Barry-John Theobald, Anurag Ranjan, Ahmed Hussein Abdelaziz, Nicholas Apostoloff

Images generated using MorphGAN conserve the identity of the person in the original image, and the provided control over head pose and facial expression allows test sets to be created to identify robustness issues of a facial recognition deep network with respect to pose and expression.

Data Augmentation Face Generation +1

Modality Dropout for Improved Performance-driven Talking Faces

no code implementations27 May 2020 Ahmed Hussen Abdelaziz, Barry-John Theobald, Paul Dixon, Reinhard Knothe, Nicholas Apostoloff, Sachin Kajareker

We use subjective testing to demonstrate: 1) the improvement of audiovisual-driven animation over the equivalent video-only approach, and 2) the improvement in the animation of speech-related facial movements after introducing modality dropout.

Finding Experts in Transformer Models

no code implementations15 May 2020 Xavier Suau, Luca Zappella, Nicholas Apostoloff

We show that expert units are important in several ways: (1) The presence of expert units is correlated ($r^2=0. 833$) with the generalization power of TM, which allows ranking TM without requiring fine-tuning on suites of downstream tasks.

Mirroring to Build Trust in Digital Assistants

no code implementations2 Apr 2019 Katherine Metcalf, Barry-John Theobald, Garrett Weinberg, Robert Lee, Ing-Marie Jonsson, Russ Webb, Nicholas Apostoloff

We describe experiments towards building a conversational digital assistant that considers the preferred conversational style of the user.

Learning Sharing Behaviors with Arbitrary Numbers of Agents

no code implementations10 Dec 2018 Katherine Metcalf, Barry-John Theobald, Nicholas Apostoloff

We model the individual behavior for each agent in an interaction and then use a multi-agent fusion model to generate a summary over the expected actions of the group to render the model independent of the number of agents.


Filter Distillation for Network Compression

no code implementations ICLR 2019 Xavier Suau, Luca Zappella, Nicholas Apostoloff

We propose two algorithms: the first allows users to target compression to specific network property, such as number of trainable variable (footprint), and produces a compressed model that satisfies the requested property while preserving the maximum amount of spectral energy in the responses of each layer, while the second is a parameter-free heuristic that selects the compression used at each layer by trying to mimic an ideal set of uncorrelated responses.

Domain Adaptation Neural Network Compression +1

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