Zobrazeno 21 - 30
of 61
pro vyhledávání: '"Hu, Jie"'
In this paper, we propose YOSO, a real-time panoptic segmentation framework. YOSO predicts masks via dynamic convolutions between panoptic kernels and image feature maps, in which you only need to segment once for both instance and semantic segmentat
Externí odkaz:
http://arxiv.org/abs/2303.14651
Deep neural networks have been proven effective in a wide range of tasks. However, their high computational and memory costs make them impractical to deploy on resource-constrained devices. To address this issue, quantization schemes have been propos
Externí odkaz:
http://arxiv.org/abs/2303.07080
Generative adversarial networks (GANs) have achieved remarkable progress in the natural image field. However, when applying GANs in the remote sensing (RS) image generation task, an extraordinary phenomenon is observed: the GAN model is more sensitiv
Externí odkaz:
http://arxiv.org/abs/2303.05240
Autor:
Ye, Suhang, Zhang, Yingyi, Hu, Jie, Cao, Liujuan, Zhang, Shengchuan, Shen, Lei, Wang, Jun, Ding, Shouhong, Ji, Rongrong
In the field of human pose estimation, regression-based methods have been dominated in terms of speed, while heatmap-based methods are far ahead in terms of performance. How to take advantage of both schemes remains a challenging problem. In this pap
Externí odkaz:
http://arxiv.org/abs/2303.02455
Autor:
Qiao, Junbo, Lin, Shaohui, Zhang, Yunlun, Li, Wei, Hu, Jie, He, Gaoqi, Wang, Changbo, Ma, Lizhuang
Real-world image super-resolution (RISR) has received increased focus for improving the quality of SR images under unknown complex degradation. Existing methods rely on the heavy SR models to enhance low-resolution (LR) images of different degradatio
Externí odkaz:
http://arxiv.org/abs/2212.07613
Recent work has shown that Binarized Neural Networks (BNNs) are able to greatly reduce computational costs and memory footprints, facilitating model deployment on resource-constrained devices. However, in comparison to their full-precision counterpar
Externí odkaz:
http://arxiv.org/abs/2112.10149
Autor:
Wang, Zerun, Xiang, Liuyu, Yang, Fan, Qian, Jinzhao, Hu, Jie, Huang, Haidong, Han, Jungong, Guo, Yuchen, Ding, Guiguang
While recent deep deblurring algorithms have achieved remarkable progress, most existing methods focus on the global deblurring problem, where the image blur mostly arises from severe camera shake. We argue that the local blur, which is mostly derive
Externí odkaz:
http://arxiv.org/abs/2109.09149
Autor:
Li, Jiangmeng, Qiang, Wenwen, Gao, Hang, Su, Bing, Razzak, Farid, Hu, Jie, Zheng, Changwen, Xiong, Hui
Multi-view representation learning captures comprehensive information from multiple views of a shared context. Recent works intuitively apply contrastive learning (CL) to learn representations, regarded as a pairwise manner, which is still scalable:
Externí odkaz:
http://arxiv.org/abs/2109.02344
The nonlocal-based blocks are designed for capturing long-range spatial-temporal dependencies in computer vision tasks. Although having shown excellent performance, they still lack the mechanism to encode the rich, structured information among elemen
Externí odkaz:
http://arxiv.org/abs/2108.02451
Publikováno v:
IEEE Transactions on Engineering Management. Published Online. 2022
In large technology companies, the requirements for managing and organizing technical documents created by engineers and managers have increased dramatically in recent years, which has led to a higher demand for more scalable, accurate, and automated
Externí odkaz:
http://arxiv.org/abs/2106.14269