Zobrazeno 1 - 10
of 389
pro vyhledávání: '"Hall, Melissa"'
Autor:
Sureddy, Abhishek, Padalia, Dishant, Periyakaruppa, Nandhinee, Saha, Oindrila, Williams, Adina, Romero-Soriano, Adriana, Richards, Megan, Kirichenko, Polina, Hall, Melissa
Recent work has identified substantial disparities in generated images of different geographic regions, including stereotypical depictions of everyday objects like houses and cars. However, existing measures for these disparities have been limited to
Externí odkaz:
http://arxiv.org/abs/2406.11988
Autor:
Astolfi, Pietro, Careil, Marlene, Hall, Melissa, Mañas, Oscar, Muckley, Matthew, Verbeek, Jakob, Soriano, Adriana Romero, Drozdzal, Michal
Building world models that accurately and comprehensively represent the real world is the utmost aspiration for conditional image generative models as it would enable their use as world simulators. For these models to be successful world models, they
Externí odkaz:
http://arxiv.org/abs/2406.10429
Autor:
Hemmat, Reyhane Askari, Hall, Melissa, Sun, Alicia, Ross, Candace, Drozdzal, Michal, Romero-Soriano, Adriana
With the growing popularity of text-to-image generative models, there has been increasing focus on understanding their risks and biases. Recent work has found that state-of-the-art models struggle to depict everyday objects with the true diversity of
Externí odkaz:
http://arxiv.org/abs/2406.04551
Autor:
Bordes, Florian, Pang, Richard Yuanzhe, Ajay, Anurag, Li, Alexander C., Bardes, Adrien, Petryk, Suzanne, Mañas, Oscar, Lin, Zhiqiu, Mahmoud, Anas, Jayaraman, Bargav, Ibrahim, Mark, Hall, Melissa, Xiong, Yunyang, Lebensold, Jonathan, Ross, Candace, Jayakumar, Srihari, Guo, Chuan, Bouchacourt, Diane, Al-Tahan, Haider, Padthe, Karthik, Sharma, Vasu, Xu, Hu, Tan, Xiaoqing Ellen, Richards, Megan, Lavoie, Samuel, Astolfi, Pietro, Hemmat, Reyhane Askari, Chen, Jun, Tirumala, Kushal, Assouel, Rim, Moayeri, Mazda, Talattof, Arjang, Chaudhuri, Kamalika, Liu, Zechun, Chen, Xilun, Garrido, Quentin, Ullrich, Karen, Agrawal, Aishwarya, Saenko, Kate, Celikyilmaz, Asli, Chandra, Vikas
Following the recent popularity of Large Language Models (LLMs), several attempts have been made to extend them to the visual domain. From having a visual assistant that could guide us through unfamiliar environments to generative models that produce
Externí odkaz:
http://arxiv.org/abs/2405.17247
Autor:
Hall, Melissa, Bell, Samuel J., Ross, Candace, Williams, Adina, Drozdzal, Michal, Soriano, Adriana Romero
Rapid progress in text-to-image generative models coupled with their deployment for visual content creation has magnified the importance of thoroughly evaluating their performance and identifying potential biases. In pursuit of models that generate i
Externí odkaz:
http://arxiv.org/abs/2405.04457
Autor:
Mañas, Oscar, Astolfi, Pietro, Hall, Melissa, Ross, Candace, Urbanek, Jack, Williams, Adina, Agrawal, Aishwarya, Romero-Soriano, Adriana, Drozdzal, Michal
Impressive advances in text-to-image (T2I) generative models have yielded a plethora of high performing models which are able to generate aesthetically appealing, photorealistic images. Despite the progress, these models still struggle to produce ima
Externí odkaz:
http://arxiv.org/abs/2403.17804
Errors in labels obtained via human annotation adversely affect a model's performance. Existing approaches propose ways to mitigate the effect of label error on a model's downstream accuracy, yet little is known about its impact on a model's disparit
Externí odkaz:
http://arxiv.org/abs/2310.02533
Autor:
Sun, Jiachen, Ibrahim, Mark, Hall, Melissa, Evtimov, Ivan, Mao, Z. Morley, Ferrer, Cristian Canton, Hazirbas, Caner
Textual prompt tuning has demonstrated significant performance improvements in adapting natural language processing models to a variety of downstream tasks by treating hand-engineered prompts as trainable parameters. Inspired by the success of textua
Externí odkaz:
http://arxiv.org/abs/2309.15251
Autor:
Gustafson, Laura, Rolland, Chloe, Ravi, Nikhila, Duval, Quentin, Adcock, Aaron, Fu, Cheng-Yang, Hall, Melissa, Ross, Candace
Computer vision models have known performance disparities across attributes such as gender and skin tone. This means during tasks such as classification and detection, model performance differs for certain classes based on the demographics of the peo
Externí odkaz:
http://arxiv.org/abs/2309.00035
Autor:
Hall, Melissa, Ross, Candace, Williams, Adina, Carion, Nicolas, Drozdzal, Michal, Soriano, Adriana Romero
The unprecedented photorealistic results achieved by recent text-to-image generative systems and their increasing use as plug-and-play content creation solutions make it crucial to understand their potential biases. In this work, we introduce three i
Externí odkaz:
http://arxiv.org/abs/2308.06198