Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Denton, Remi"'
Autor:
Jha, Akshita, Prabhakaran, Vinodkumar, Denton, Remi, Laszlo, Sarah, Dave, Shachi, Qadri, Rida, Reddy, Chandan K., Dev, Sunipa
Recent studies have shown that Text-to-Image (T2I) model generations can reflect social stereotypes present in the real world. However, existing approaches for evaluating stereotypes have a noticeable lack of coverage of global identity groups and th
Externí odkaz:
http://arxiv.org/abs/2401.06310
Publikováno v:
2023 ACM Conference on Fairness, Accountability, and Transparency (FAccT '23)
This paper presents a community-centered study of cultural limitations of text-to-image (T2I) models in the South Asian context. We theorize these failures using scholarship on dominant media regimes of representations and locate them within particip
Externí odkaz:
http://arxiv.org/abs/2305.11844
Human annotations play a crucial role in machine learning (ML) research and development. However, the ethical considerations around the processes and decisions that go into building ML datasets has not received nearly enough attention. In this paper,
Externí odkaz:
http://arxiv.org/abs/2112.04554
Autor:
Denton, Remi, Hanna, Alex, Amironesei, Razvan, Smart, Andrew, Nicole, Hilary, Scheuerman, Morgan Klaus
In response to algorithmic unfairness embedded in sociotechnical systems, significant attention has been focused on the contents of machine learning datasets which have revealed biases towards white, cisgender, male, and Western data subjects. In con
Externí odkaz:
http://arxiv.org/abs/2007.07399
Facial analysis models are increasingly used in applications that have serious impacts on people's lives, ranging from authentication to surveillance tracking. It is therefore critical to develop techniques that can reveal unintended biases in facial
Externí odkaz:
http://arxiv.org/abs/1906.06439
Autor:
Denton, Remi, Fergus, Rob
Generating video frames that accurately predict future world states is challenging. Existing approaches either fail to capture the full distribution of outcomes, or yield blurry generations, or both. In this paper we introduce an unsupervised video g
Externí odkaz:
http://arxiv.org/abs/1802.07687
Autor:
Denton, Remi, Birodkar, Vighnesh
We present a new model DrNET that learns disentangled image representations from video. Our approach leverages the temporal coherence of video and a novel adversarial loss to learn a representation that factorizes each frame into a stationary part an
Externí odkaz:
http://arxiv.org/abs/1705.10915
We introduce a simple semi-supervised learning approach for images based on in-painting using an adversarial loss. Images with random patches removed are presented to a generator whose task is to fill in the hole, based on the surrounding pixels. The
Externí odkaz:
http://arxiv.org/abs/1611.06430
Autor:
Gebru, Timnit, Denton, Remi
Publikováno v:
Foundations & Trends in Computer Graphics & Vision; 2024, Vol. 16 Issue 3, p215-321, 107p
We present techniques for speeding up the test-time evaluation of large convolutional networks, designed for object recognition tasks. These models deliver impressive accuracy but each image evaluation requires millions of floating point operations,
Externí odkaz:
http://arxiv.org/abs/1404.0736