Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Baradad, Manel"'
Autor:
Sharma, Pratyusha, Shaham, Tamar Rott, Baradad, Manel, Fu, Stephanie, Rodriguez-Munoz, Adrian, Duggal, Shivam, Isola, Phillip, Torralba, Antonio
What does learning to model relationships between strings teach large language models (LLMs) about the visual world? We systematically evaluate LLMs' abilities to generate and recognize an assortment of visual concepts of increasing complexity and th
Externí odkaz:
http://arxiv.org/abs/2401.01862
Autor:
Baradad, Manel, Li, Yuanzhen, Cole, Forrester, Rubinstein, Michael, Torralba, Antonio, Freeman, William T., Jampani, Varun
Estimating the depth of objects from a single image is a valuable task for many vision, robotics, and graphics applications. However, current methods often fail to produce accurate depth for objects in diverse scenes. In this work, we propose a simpl
Externí odkaz:
http://arxiv.org/abs/2306.05428
We introduce Deep Augmentation, an approach to implicit data augmentation using dropout or PCA to transform a targeted layer within a neural network to improve performance and generalization. We demonstrate Deep Augmentation through extensive experim
Externí odkaz:
http://arxiv.org/abs/2303.14537
Autor:
Baradad, Manel, Chen, Chun-Fu, Wulff, Jonas, Wang, Tongzhou, Feris, Rogerio, Torralba, Antonio, Isola, Phillip
Publikováno v:
NeurIPS 2022
Learning image representations using synthetic data allows training neural networks without some of the concerns associated with real images, such as privacy and bias. Existing work focuses on a handful of curated generative processes which require e
Externí odkaz:
http://arxiv.org/abs/2211.16412
Autor:
Baradad, Manel
Current vision systems are trained on huge datasets, and these datasets come with costs: curation is expensive, they inherit human biases, and there are concerns over privacy and usage rights. To counter these costs, interest has surged in learning f
Externí odkaz:
https://hdl.handle.net/1721.1/140140
Current vision systems are trained on huge datasets, and these datasets come with costs: curation is expensive, they inherit human biases, and there are concerns over privacy and usage rights. To counter these costs, interest has surged in learning f
Externí odkaz:
http://arxiv.org/abs/2106.05963
Autor:
Salvador, Amaia, Bellver, Miriam, Campos, Victor, Baradad, Manel, Marques, Ferran, Torres, Jordi, Giro-i-Nieto, Xavier
We present a recurrent model for semantic instance segmentation that sequentially generates binary masks and their associated class probabilities for every object in an image. Our proposed system is trainable end-to-end from an input image to a seque
Externí odkaz:
http://arxiv.org/abs/1712.00617
We introduce Deep Augmentation, an approach to data augmentation using dropout to dynamically transform a targeted layer within a neural network, with the option to use the stop-gradient operation, offering significant improvements in model performan
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e960c408ae020657f6c665788074851d
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Zamora, Marti, Baradad, Manel, Amado, Ester, Cordomi, Silvia, Limon, Esther, Ribera, Juliana, Arias, Marta, Gavalda, Ricard
Publikováno v:
2015 IEEE International Conference on Data Science & Advanced Analytics (DSAA); 2015, p1-9, 9p
