Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Guan, Bochen"'
The Segment Anything Model (SAM) has exhibited outstanding performance in various image segmentation tasks. Despite being trained with over a billion masks, SAM faces challenges in mask prediction quality in numerous scenarios, especially in real-wor
Externí odkaz:
http://arxiv.org/abs/2401.13051
Recent approaches such as ControlNet offer users fine-grained spatial control over text-to-image (T2I) diffusion models. However, auxiliary modules have to be trained for each type of spatial condition, model architecture, and checkpoint, putting the
Externí odkaz:
http://arxiv.org/abs/2312.07536
Autor:
Shang, Liang, Liu, Yanli, Lou, Zhengyang, Quan, Shuxue, Adluru, Nagesh, Guan, Bochen, Sethares, William A.
Convolutional neural networks (CNNs) and vision transformers (ViTs) have achieved remarkable success in various vision tasks. However, many architectures do not consider interactions between feature maps from different stages and scales, which may li
Externí odkaz:
http://arxiv.org/abs/2308.05872
Autor:
Lou, Zhengyang, Xu, Huan, Mu, Fangzhou, Liu, Yanli, Zhang, Xiaoyu, Shang, Liang, Li, Jiang, Guan, Bochen, Li, Yin, Hu, Yu Hen
Deep models have demonstrated recent success in single-image dehazing. Most prior methods consider fully supervised training and learn from paired clean and hazy images, where a hazy image is synthesized based on a clean image and its estimated depth
Externí odkaz:
http://arxiv.org/abs/2305.16481
For many years, the family of convolutional neural networks (CNNs) has been a workhorse in deep learning. Recently, many novel CNN structures have been designed to address increasingly challenging tasks. To make them work efficiently on edge devices,
Externí odkaz:
http://arxiv.org/abs/2110.10842
The memory consumption of most Convolutional Neural Network (CNN) architectures grows rapidly with increasing depth of the network, which is a major constraint for efficient network training on modern GPUs with limited memory, embedded systems, and m
Externí odkaz:
http://arxiv.org/abs/1905.10915
Estimation of the frequency and duration of logos in videos is important and challenging in the advertisement industry as a way of estimating the impact of ad purchases. Since logos occupy only a small area in the videos, the popular methods of image
Externí odkaz:
http://arxiv.org/abs/1808.03735
Autor:
Zhang, Xiao, Chen, Youjian, Wang, Yuzhu, Lin, Jun Yu, Hu, Nai Chao, Guan, Bochen, Lee, Ching Hua
Publikováno v:
Phys. Rev. B 100, 041110 (2019)
Recently, there has been a drive towards the realization of topological phases beyond conventional electronic materials, including phases defined in more than three dimensions. We propose a versatile and experimentally realistic approach of realizing
Externí odkaz:
http://arxiv.org/abs/1710.08385
In the recent years, there has been a drive towards the realization of topological phases beyond conventional electronic materials, including phases defined in more than three dimensions. We propose a way to realize 2nd Chern number topological phase
Externí odkaz:
http://arxiv.org/abs/1612.08687
Publikováno v:
Scientific Reports 5, Article number: 18008 (2015)
Materials exhibiting negative differential resistance have important applications in technologies involving microwave generation, which range from motion sensing to radio astronomy. Despite their usefulness, there has been few physical mechanisms giv
Externí odkaz:
http://arxiv.org/abs/1503.01097