Zobrazeno 1 - 10
of 50
pro vyhledávání: '"Niu, Yi"'
Current weakly-supervised incremental learning for semantic segmentation (WILSS) approaches only consider replacing pixel-level annotations with image-level labels, while the training images are still from well-designed datasets. In this work, we arg
Externí odkaz:
http://arxiv.org/abs/2407.13363
3D object detection based on roadside cameras is an additional way for autonomous driving to alleviate the challenges of occlusion and short perception range from vehicle cameras. Previous methods for roadside 3D object detection mainly focus on mode
Externí odkaz:
http://arxiv.org/abs/2404.05280
The basic principle of the patch-matching based style transfer is to substitute the patches of the content image feature maps by the closest patches from the style image feature maps. Since the finite features harvested from one single aesthetic styl
Externí odkaz:
http://arxiv.org/abs/2309.10528
Autor:
Liu, Chang, Rizzoli, Giulia, Barbato, Francesco, Maracani, Andrea, Toldo, Marco, Michieli, Umberto, Niu, Yi, Zanuttigh, Pietro
Catastrophic forgetting of previous knowledge is a critical issue in continual learning typically handled through various regularization strategies. However, existing methods struggle especially when several incremental steps are performed. In this p
Externí odkaz:
http://arxiv.org/abs/2309.10479
Knowledge distillation learns a lightweight student model that mimics a cumbersome teacher. Existing methods regard the knowledge as the feature of each instance or their relations, which is the instance-level knowledge only from the teacher model, i
Externí odkaz:
http://arxiv.org/abs/2210.09022
Autor:
Cheng, Zhanzhan, Zhang, Peng, Li, Can, Liang, Qiao, Xu, Yunlu, Li, Pengfei, Pu, Shiliang, Niu, Yi, Wu, Fei
Recently, automatically extracting information from visually rich documents (e.g., tickets and resumes) has become a hot and vital research topic due to its widespread commercial value. Most existing methods divide this task into two subparts: the te
Externí odkaz:
http://arxiv.org/abs/2207.06744
Autor:
Qiao, Liang, Jiang, Hui, Chen, Ying, Li, Can, Li, Pengfei, Li, Zaisheng, Zou, Baorui, Guo, Dashan, Xu, Yingda, Xu, Yunlu, Cheng, Zhanzhan, Niu, Yi
This paper presents DavarOCR, an open-source toolbox for OCR and document understanding tasks. DavarOCR currently implements 19 advanced algorithms, covering 9 different task forms. DavarOCR provides detailed usage instructions and the trained models
Externí odkaz:
http://arxiv.org/abs/2207.06695
End-to-end text spotting has attached great attention recently due to its benefits on global optimization and high maintainability for real applications. However, the input scale has always been a tough trade-off since recognizing a small text instan
Externí odkaz:
http://arxiv.org/abs/2207.06694
Expandable networks have demonstrated their advantages in dealing with catastrophic forgetting problem in incremental learning. Considering that different tasks may need different structures, recent methods design dynamic structures adapted to differ
Externí odkaz:
http://arxiv.org/abs/2207.06754
Open Set Recognition (OSR) has been an emerging topic. Besides recognizing predefined classes, the system needs to reject the unknowns. Prototype learning is a potential manner to handle the problem, as its ability to improve intra-class compactness
Externí odkaz:
http://arxiv.org/abs/2203.08569