Search Results for author:
Found 35 papers, 12 papers with code
Nteasee: A mixed methods study of expert and general population perspectives on deploying AI for health in African countries
This work presents the first-of-its-kind qualitative research study of the potential of AI for health in Africa from an algorithmic fairness angle, with perspectives from both experts and the general population.
Understanding the Local Geometry of Generative Model Manifolds
Deep generative models learn continuous representations of complex data manifolds using a finite number of samples during training.
Position: Cracking the Code of Cascading Disparity Towards Marginalized Communities
The rise of foundation models holds immense promise for advancing AI, but this progress may amplify existing risks and inequalities, leaving marginalized communities behind.
A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models
Our contributions include a multifactorial framework for human assessment of LLM-generated answers for biases, and EquityMedQA, a collection of seven datasets enriched for adversarial queries.
The Case for Globalizing Fairness: A Mixed Methods Study on Colonialism, AI, and Health in Africa
Whereas experts generally expressed a shared view about the relevance of colonial history for the development and implementation of AI technologies in Africa, the majority of the general population participants surveyed did not think there was a direct link between AI and colonialism.
From plane crashes to algorithmic harm: applicability of safety engineering frameworks for responsible ML
Inappropriate design and deployment of machine learning (ML) systems leads to negative downstream social and ethical impact -- described here as social and ethical risks -- for users, society and the environment.
Bias-inducing geometries: an exactly solvable data model with fairness implications
Then, we consider a novel mitigation strategy based on a matched inference approach, consisting in the introduction of coupled learning models.
Evaluation Gaps in Machine Learning Practice
Forming a reliable judgement of a machine learning (ML) model's appropriateness for an application ecosystem is critical for its responsible use, and requires considering a broad range of factors including harms, benefits, and responsibilities.
Disability prediction in multiple sclerosis using performance outcome measures and demographic data
To the best of our knowledge, our results are the first to show that it is possible to predict disease progression using POMs and demographic data in the context of both clinical trials and smartphone-base studies by using two datasets.
Healthsheet: Development of a Transparency Artifact for Health Datasets
Our findings from the interviewee study and case studies show 1) that datasheets should be contextualized for healthcare, 2) that despite incentives to adopt accountability practices such as datasheets, there is a lack of consistency in the broader use of these practices 3) how the ML for health community views datasheets and particularly \textit{Healthsheets} as diagnostic tool to surface the limitations and strength of datasets and 4) the relative importance of different fields in the datasheet to healthcare concerns.
se-Shweshwe Inspired Fashion Generation
Fashion is one of the ways in which we show ourselves to the world.
Thinking Beyond Distributions in Testing Machine Learned Models
Testing practices within the machine learning (ML) community have centered around assessing a learned model's predictive performance measured against a test dataset, often drawn from the same distribution as the training dataset.
Ethics and Creativity in Computer Vision
This paper offers a retrospective of what we learnt from organizing the workshop *Ethical Considerations in Creative applications of Computer Vision* at CVPR 2021 conference and, prior to that, a series of workshops on *Computer Vision for Fashion, Art and Design* at ECCV 2018, ICCV 2019, and CVPR 2020.
Deep Cox Mixtures for Survival Regression
Survival analysis is a challenging variation of regression modeling because of the presence of censoring, where the outcome measurement is only partially known, due to, for example, loss to follow up.
A Few-Shot Sequential Approach for Object Counting
In this work, we address the problem of few-shot multi-class object counting with point-level annotations.
Post-Workshop Report on Science meets Engineering in Deep Learning, NeurIPS 2019, Vancouver
Science meets Engineering in Deep Learning took place in Vancouver as part of the Workshop section of NeurIPS 2019.
Reinforced active learning for image segmentation
Our method proposes a new modification of the deep Q-network (DQN) formulation for active learning, adapting it to the large-scale nature of semantic segmentation problems.
Neural Multisensory Scene Inference
For embodied agents to infer representations of the underlying 3D physical world they inhabit, they should efficiently combine multisensory cues from numerous trials, e. g., by looking at and touching objects.
Retrieving Signals in the Frequency Domain with Deep Complex Extractors
Using the Wall Street Journal Dataset, we compare our phase-aware loss to several others that operate both in the time and frequency domains and demonstrate the effectiveness of our proposed signal extraction method and proposed loss.
Retrieving Signals with Deep Complex Extractors
Building on recent advances, we propose a new deep complex-valued method for signal retrieval and extraction in the frequency domain.
Instance Segmentation with Point Supervision
Instance segmentation methods often require costly per-pixel labels.
CLAREL: Classification via retrieval loss for zero-shot learning
We address the problem of learning fine-grained cross-modal representations.
Reinforced Imitation Learning from Observations
Imitation learning is an effective alternative approach to learn a policy when the reward function is sparse.
Reinforced Imitation in Heterogeneous Action Space
Imitation learning is an effective alternative approach to learn a policy when the reward function is sparse.
Multi-Class Few Shot Learning Task and Controllable Environment
In this paper, we address the task of classifying multiple objects by seeing only a few samples from each category.
Towards Standardization of Data Licenses: The Montreal Data License
This paper provides a taxonomy for the licensing of data in the fields of artificial intelligence and machine learning.
Adaptive Cross-Modal Few-Shot Learning
Through a series of experiments, we show that by this adaptive combination of the two modalities, our model outperforms current uni-modality few-shot learning methods and modality-alignment methods by a large margin on all benchmarks and few-shot scenarios tested.
Adversarial Framing for Image and Video Classification
Neural networks are prone to adversarial attacks.
Domain-Adaptive Single-View 3D Reconstruction
In this paper, we propose a framework to improve over these challenges using adversarial training.
Where are the Blobs: Counting by Localization with Point Supervision
However, we propose a detection-based method that does not need to estimate the size and shape of the objects and that outperforms regression-based methods.
Ranked #1 on
Object Counting
on Pascal VOC 2007 count-test
Fashion-Gen: The Generative Fashion Dataset and Challenge
We introduce a new dataset of 293, 008 high definition (1360 x 1360 pixels) fashion images paired with item descriptions provided by professional stylists.
Uncertainty in Multitask Transfer Learning
The result is a rich and meaningful prior capable of few-shot learning on new tasks.
Hierarchical Adversarially Learned Inference
We propose a novel hierarchical generative model with a simple Markovian structure and a corresponding inference model.
Deep Prior
The recent literature on deep learning offers new tools to learn a rich probability distribution over high dimensional data such as images or sounds.
Deep Complex Networks
Despite their attractive properties and potential for opening up entirely new neural architectures, complex-valued deep neural networks have been marginalized due to the absence of the building blocks required to design such models.
Ranked #3 on
Music Transcription
on MusicNet
