Zobrazeno 1 - 10
of 7 461
pro vyhledávání: '"Bharath. P"'
Recognition of features in satellite imagery (forests, swimming pools, etc.) depends strongly on the spatial scale of the concept and therefore the resolution of the images. This poses two challenges: Which resolution is best suited for recognizing a
Externí odkaz:
http://arxiv.org/abs/2411.00210
Autor:
Zhou, Hangyu, Kao, Chia-Hsiang, Phoo, Cheng Perng, Mall, Utkarsh, Hariharan, Bharath, Bala, Kavita
Clouds in satellite imagery pose a significant challenge for downstream applications. A major challenge in current cloud removal research is the absence of a comprehensive benchmark and a sufficiently large and diverse training dataset. To address th
Externí odkaz:
http://arxiv.org/abs/2410.23891
Class imbalance in training datasets can lead to bias and poor generalization in machine learning models. While pre-processing of training datasets can efficiently address both these issues in centralized learning environments, it is challenging to d
Externí odkaz:
http://arxiv.org/abs/2410.21192
In this study, we investigate the under-explored intervention planning aimed at disseminating accurate information within dynamic opinion networks by leveraging learning strategies. Intervention planning involves identifying key nodes (search) and ex
Externí odkaz:
http://arxiv.org/abs/2410.14091
Arterial spin labeling (ASL) magnetic resonance imaging (MRI) enables cerebral perfusion measurement, which is crucial in detecting and managing neurological issues in infants born prematurely or after perinatal complications. However, cerebral blood
Externí odkaz:
http://arxiv.org/abs/2410.19759
Autor:
Yoo, Jinsu, Feng, Zhenyang, Pan, Tai-Yu, Sun, Yihong, Phoo, Cheng Perng, Chen, Xiangyu, Campbell, Mark, Weinberger, Kilian Q., Hariharan, Bharath, Chao, Wei-Lun
Accurate 3D object detection in real-world environments requires a huge amount of annotated data with high quality. Acquiring such data is tedious and expensive, and often needs repeated effort when a new sensor is adopted or when the detector is dep
Externí odkaz:
http://arxiv.org/abs/2410.02646
Autor:
Kao, Chia-Hsiang, Hariharan, Bharath
Despite its widespread use in neural networks, error backpropagation has faced criticism for its lack of biological plausibility, suffering from issues such as the backward locking problem and the weight transport problem. These limitations have moti
Externí odkaz:
http://arxiv.org/abs/2409.19841
Autor:
He, Zizhao, Li, Rui, Shu, Yiping, Tortora, Crescenzo, Er, Xinzhong, Canameras, Raoul, Schuldt, Stefan, Napolitano, Nicola R., N, Bharath Chowdhary, Chen, Qihang, Li, Nan, Feng, Haicheng, Deng, Limeng, Li, Guoliang, Koopmans, L. V. E., Dvornik, Andrej
Gravitationally strongly lensed quasars (SL-QSO) offer invaluable insights into cosmological and astrophysical phenomena. With the data from ongoing and next-generation surveys, thousands of SL-QSO systems can be discovered expectedly, leading to unp
Externí odkaz:
http://arxiv.org/abs/2409.17471
Autor:
Li, Zilu, Yang, Guandao, Zhao, Qingqing, Deng, Xi, Guibas, Leonidas, Hariharan, Bharath, Wetzstein, Gordon
Publikováno v:
SIGGRAPH Conference Papers 2024
This paper presents a method to leverage arbitrary neural network architecture for control variates. Control variates are crucial in reducing the variance of Monte Carlo integration, but they hinge on finding a function that both correlates with the
Externí odkaz:
http://arxiv.org/abs/2409.15394
Autor:
Chen, Zonghao, Mustafi, Aratrika, Glaser, Pierre, Korba, Anna, Gretton, Arthur, Sriperumbudur, Bharath K.
We introduce a (de)-regularization of the Maximum Mean Discrepancy (DrMMD) and its Wasserstein gradient flow. Existing gradient flows that transport samples from source distribution to target distribution with only target samples, either lack tractab
Externí odkaz:
http://arxiv.org/abs/2409.14980