Zobrazeno 1 - 10
of 60
pro vyhledávání: '"Hu, Jie"'
Autor:
Tian, Yuchuan, Han, Jianhong, Chen, Hanting, Xi, Yuanyuan, Zhang, Guoyang, Hu, Jie, Xu, Chao, Wang, Yunhe
Due to the unaffordable size and intensive computation costs of low-level vision models, All-in-One models that are designed to address a handful of low-level vision tasks simultaneously have been popular. However, existing All-in-One models are limi
Externí odkaz:
http://arxiv.org/abs/2407.00676
Semi-Supervised Instance Segmentation (SSIS) aims to leverage an amount of unlabeled data during training. Previous frameworks primarily utilized the RGB information of unlabeled images to generate pseudo-labels. However, such a mechanism often intro
Externí odkaz:
http://arxiv.org/abs/2406.17413
Autor:
Chen, Yirui, Huang, Xudong, Zhang, Quan, Li, Wei, Zhu, Mingjian, Yan, Qiangyu, Li, Simiao, Chen, Hanting, Hu, Hailin, Yang, Jie, Liu, Wei, Hu, Jie
The extraordinary ability of generative models emerges as a new trend in image editing and generating realistic images, posing a serious threat to the trustworthiness of multimedia data and driving the research of image manipulation detection and loc
Externí odkaz:
http://arxiv.org/abs/2406.16531
Recent semi-supervised object detection (SSOD) has achieved remarkable progress by leveraging unlabeled data for training. Mainstream SSOD methods rely on Consistency Regularization methods and Exponential Moving Average (EMA), which form a cyclic da
Externí odkaz:
http://arxiv.org/abs/2405.13374
Diffusion Transformers (DiTs) introduce the transformer architecture to diffusion tasks for latent-space image generation. With an isotropic architecture that chains a series of transformer blocks, DiTs demonstrate competitive performance and good sc
Externí odkaz:
http://arxiv.org/abs/2405.02730
Anomaly synthesis is one of the effective methods to augment abnormal samples for training. However, current anomaly synthesis methods predominantly rely on texture information as input, which limits the fidelity of synthesized abnormal samples. Beca
Externí odkaz:
http://arxiv.org/abs/2404.19444
Autor:
Luo, Yongdong, Lin, Haojia, Zheng, Xiawu, Jiang, Yigeng, Chao, Fei, Hu, Jie, Jiang, Guannan, Zhang, Songan, Ji, Rongrong
3D Visual Grounding (3DVG) and 3D Dense Captioning (3DDC) are two crucial tasks in various 3D applications, which require both shared and complementary information in localization and visual-language relationships. Therefore, existing approaches adop
Externí odkaz:
http://arxiv.org/abs/2404.11064
Autor:
Qiao, Junbo, Li, Wei, Xie, Haizhen, Chen, Hanting, Zhou, Yunshuai, Tu, Zhijun, Hu, Jie, Lin, Shaohui
Transformer is leading a trend in the field of image processing. Despite the great success that existing lightweight image processing transformers have achieved, they are tailored to FLOPs or parameters reduction, rather than practical inference acce
Externí odkaz:
http://arxiv.org/abs/2404.06075
Autor:
Li, Simiao, Zhang, Yun, Li, Wei, Chen, Hanting, Wang, Wenjia, Jing, Bingyi, Lin, Shaohui, Hu, Jie
Knowledge distillation (KD) is a promising yet challenging model compression technique that transfers rich learning representations from a well-performing but cumbersome teacher model to a compact student model. Previous methods for image super-resol
Externí odkaz:
http://arxiv.org/abs/2404.02573
Recent advances have demonstrated the powerful capability of transformer architecture in image restoration. However, our analysis indicates that existing transformerbased methods can not establish both exact global and local dependencies simultaneous
Externí odkaz:
http://arxiv.org/abs/2404.00633