Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Öztireli, Cengiz"'
We address prevailing challenges of the brain-powered research, departing from the observation that the literature hardly recover accurate spatial information and require subject-specific models. To address these challenges, we propose UMBRAE, a unif
Externí odkaz:
http://arxiv.org/abs/2404.07202
Autor:
Huang, Xingchang, Salaün, Corentin, Vasconcelos, Cristina, Theobalt, Christian, Öztireli, Cengiz, Singh, Gurprit
Most of the existing diffusion models use Gaussian noise for training and sampling across all time steps, which may not optimally account for the frequency contents reconstructed by the denoising network. Despite the diverse applications of correlate
Externí odkaz:
http://arxiv.org/abs/2402.04930
To comply with AI and data regulations, the need to forget private or copyrighted information from trained machine learning models is increasingly important. The key challenge in unlearning is forgetting the necessary data in a timely manner, while p
Externí odkaz:
http://arxiv.org/abs/2402.01401
In this work we present DREAM, an fMRI-to-image method for reconstructing viewed images from brain activities, grounded on fundamental knowledge of the human visual system. We craft reverse pathways that emulate the hierarchical and parallel nature o
Externí odkaz:
http://arxiv.org/abs/2310.02265
Plants are dynamic organisms and understanding temporal variations in vegetation is an essential problem for robots in the wild. However, associating repeated 3D scans of plants across time is challenging. A key step in this process is re-identifying
Externí odkaz:
http://arxiv.org/abs/2209.11526
We propose a learning-based method for light-path construction in path tracing algorithms, which iteratively optimizes and samples from what we refer to as spatio-directional Gaussian mixture models (SDMMs). In particular, we approximate incident rad
Externí odkaz:
http://arxiv.org/abs/2111.13094
Structured pruning is a well-known technique to reduce the storage size and inference cost of neural networks. The usual pruning pipeline consists of ranking the network internal filters and activations with respect to their contributions to the netw
Externí odkaz:
http://arxiv.org/abs/2006.01795
We propose Differentiable Surface Splatting (DSS), a high-fidelity differentiable renderer for point clouds. Gradients for point locations and normals are carefully designed to handle discontinuities of the rendering function. Regularization terms ar
Externí odkaz:
http://arxiv.org/abs/1906.04173
Publikováno v:
PMLR 97 (2019) 272-281
The problem of explaining the behavior of deep neural networks has recently gained a lot of attention. While several attribution methods have been proposed, most come without strong theoretical foundations, which raises questions about their reliabil
Externí odkaz:
http://arxiv.org/abs/1903.10992
The convergence speed of stochastic gradient descent (SGD) can be improved by actively selecting mini-batches. We explore sampling schemes where similar data points are less likely to be selected in the same mini-batch. In particular, we prove that s
Externí odkaz:
http://arxiv.org/abs/1804.02772