Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Xie, Hanchen"'
Modern deep learning models have demonstrated outstanding performance on discovering the underlying mechanisms when both visual appearance and intrinsic relations (e.g., causal structure) data are sufficient, such as Disentangled Representation Learn
Externí odkaz:
http://arxiv.org/abs/2408.17363
Despite the success of vision-based dynamics prediction models, which predict object states by utilizing RGB images and simple object descriptions, they were challenged by environment misalignments. Although the literature has demonstrated that unify
Externí odkaz:
http://arxiv.org/abs/2408.15201
Accurate estimation of counterfactual outcomes in high-dimensional data is crucial for decision-making and understanding causal relationships and intervention outcomes in various domains, including healthcare, economics, and social sciences. However,
Externí odkaz:
http://arxiv.org/abs/2407.20553
Autor:
Li, Jiazhi, Khayatkhoei, Mahyar, Zhu, Jiageng, Xie, Hanchen, Hussein, Mohamed E., AbdAlmageed, Wael
Ensuring a neural network is not relying on protected attributes (e.g., race, sex, age) for prediction is crucial in advancing fair and trustworthy AI. While several promising methods for removing attribute bias in neural networks have been proposed,
Externí odkaz:
http://arxiv.org/abs/2311.07141
Autor:
Li, Jiazhi, Khayatkhoei, Mahyar, Zhu, Jiageng, Xie, Hanchen, Hussein, Mohamed E., AbdAlmageed, Wael
Ensuring a neural network is not relying on protected attributes (e.g., race, sex, age) for predictions is crucial in advancing fair and trustworthy AI. While several promising methods for removing attribute bias in neural networks have been proposed
Externí odkaz:
http://arxiv.org/abs/2310.04955
Autor:
Zhu, Jiageng, Xie, Hanchen, Wu, Jianhua, Li, Jiazhi, Khayatkhoei, Mahyar, Hussein, Mohamed E., AbdAlmageed, Wael
Discovering causal relations among semantic factors is an emergent topic in representation learning. Most causal representation learning (CRL) methods are fully supervised, which is impractical due to costly labeling. To resolve this restriction, wea
Externí odkaz:
http://arxiv.org/abs/2308.05707
Autor:
Xie, Hanchen, Zhu, Jiageng, Khayatkhoei, Mahyar, Li, Jiazhi, Hussein, Mohamed E., AbdAlmageed, Wael
Dynamics prediction, which is the problem of predicting future states of scene objects based on current and prior states, is drawing increasing attention as an instance of learning physics. To solve this problem, Region Proposal Convolutional Interac
Externí odkaz:
http://arxiv.org/abs/2305.07648
Representation disentanglement is an important goal of representation learning that benefits various downstream tasks. To achieve this goal, many unsupervised learning representation disentanglement approaches have been developed. However, the traini
Externí odkaz:
http://arxiv.org/abs/2209.10623
Disentangled and invariant representations are two critical goals of representation learning and many approaches have been proposed to achieve either one of them. However, those two goals are actually complementary to each other so that we propose a
Externí odkaz:
http://arxiv.org/abs/2209.06827
Causal representation learning has been proposed to encode relationships between factors presented in the high dimensional data. However, existing methods suffer from merely using a large amount of labeled data and ignore the fact that samples genera
Externí odkaz:
http://arxiv.org/abs/2206.01802