Zobrazeno 1 - 10
of 41
pro vyhledávání: '"Ruozzi, Nicholas"'
Novel Instance Detection and Segmentation (NIDS) aims at detecting and segmenting novel object instances given a few examples of each instance. We propose a unified framework (NIDS-Net) comprising object proposal generation, embedding creation for bo
Externí odkaz:
http://arxiv.org/abs/2405.17859
Autor:
Peddi, Rohith, Arya, Shivvrat, Challa, Bharath, Pallapothula, Likhitha, Vyas, Akshay, Gouripeddi, Bhavya, Wang, Jikai, Zhang, Qifan, Komaragiri, Vasundhara, Ragan, Eric, Ruozzi, Nicholas, Xiang, Yu, Gogate, Vibhav
Following step-by-step procedures is an essential component of various activities carried out by individuals in their daily lives. These procedures serve as a guiding framework that helps to achieve goals efficiently, whether it is assembling furnitu
Externí odkaz:
http://arxiv.org/abs/2312.14556
Autor:
Lu, Yangxiao, Khargonkar, Ninad, Xu, Zesheng, Averill, Charles, Palanisamy, Kamalesh, Hang, Kaiyu, Guo, Yunhui, Ruozzi, Nicholas, Xiang, Yu
We introduce a novel robotic system for improving unseen object instance segmentation in the real world by leveraging long-term robot interaction with objects. Previous approaches either grasp or push an object and then obtain the segmentation mask o
Externí odkaz:
http://arxiv.org/abs/2302.03793
Segmenting unseen objects from images is a critical perception skill that a robot needs to acquire. In robot manipulation, it can facilitate a robot to grasp and manipulate unseen objects. Mean shift clustering is a widely used method for image segme
Externí odkaz:
http://arxiv.org/abs/2211.11679
Statistical Relational Learning (SRL) models have attracted significant attention due to their ability to model complex data while handling uncertainty. However, most of these models have been limited to discrete domains due to their limited potentia
Externí odkaz:
http://arxiv.org/abs/2110.09647
Autor:
Nourani, Mahsan, Roy, Chiradeep, Rahman, Tahrima, Ragan, Eric D., Ruozzi, Nicholas, Gogate, Vibhav
Explainable machine learning and artificial intelligence models have been used to justify a model's decision-making process. This added transparency aims to help improve user performance and understanding of the underlying model. However, in practice
Externí odkaz:
http://arxiv.org/abs/2005.02335
A variety of lifted inference algorithms, which exploit model symmetry to reduce computational cost, have been proposed to render inference tractable in probabilistic relational models. Most existing lifted inference algorithms operate only over disc
Externí odkaz:
http://arxiv.org/abs/2001.02773
Variational Auto-Encoders (VAEs) have been widely applied for learning compact, low-dimensional latent representations of high-dimensional data. When the correlation structure among data points is available, previous work proposed Correlated Variatio
Externí odkaz:
http://arxiv.org/abs/1906.06419
Variational Auto-Encoders (VAEs) are capable of learning latent representations for high dimensional data. However, due to the i.i.d. assumption, VAEs only optimize the singleton variational distributions and fail to account for the correlations betw
Externí odkaz:
http://arxiv.org/abs/1905.05335
We propose a simple and easy to implement neural network compression algorithm that achieves results competitive with more complicated state-of-the-art methods. The key idea is to modify the original optimization problem by adding K independent Gauss
Externí odkaz:
http://arxiv.org/abs/1806.05355