title={UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation},
author={ Zhou, Z. and Siddiquee, Mmr and Tajbakhsh, N. and Liang, J. },
journal={IEEE Transactions on Medical Imaging},
volume={39},
number={6},
pages={1856-1867},
year={2020},
}
@dataset{jiang_hou_2021_5171712,
author = {Jiang Hou and
Yao Ling and
Liu Yujun},
title = {{Multi-resolution dataset for photovoltaic panel
segmentation from satellite and aerial imagery}},
month = aug,
year = 2021,
note = {{Data document can refer to the preprint https://es
sd.copernicus.org/preprints/essd-2021-270/}},
publisher = {Zenodo},
version = {v1.0},
doi = {10.5281/zenodo.5171712},
url = {https://doi.org/10.5281/zenodo.5171712}
}
@article{devlin2018bert,
title={Bert: Pre-training of deep bidirectional transformers for language understanding},
author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
journal={arXiv preprint arXiv:1810.04805},
year={2018}
}
@inproceedings{radford2021learning,
title={Learning transferable visual models from natural language supervision},
author={Radford, Alec and Kim, Jong Wook and Hallacy, Chris and Ramesh, Aditya and Goh, Gabriel and Agarwal, Sandhini and Sastry, Girish and Askell, Amanda and Mishkin, Pamela and Clark, Jack and others},
booktitle={International Conference on Machine Learning},
pages={8748--8763},
year={2021},
organization={PMLR}
}
@inproceedings{wang2020large,
title={A large-scale chinese short-text conversation dataset},
author={Wang, Yida and Ke, Pei and Zheng, Yinhe and Huang, Kaili and Jiang, Yong and Zhu, Xiaoyan and Huang, Minlie},
booktitle={CCF International Conference on Natural Language Processing and Chinese Computing},
abstract = "Multi-task learning with transformer encoders (MTL) has emerged as a powerful technique to improve performance on closely-related tasks for both accuracy and efficiency while a question still remains whether or not it would perform as well on tasks that are distinct in nature. We first present MTL results on five NLP tasks, POS, NER, DEP, CON, and SRL, and depict its deficiency over single-task learning. We then conduct an extensive pruning analysis to show that a certain set of attention heads get claimed by most tasks during MTL, who interfere with one another to fine-tune those heads for their own objectives. Based on this finding, we propose the Stem Cell Hypothesis to reveal the existence of attention heads naturally talented for many tasks that cannot be jointly trained to create adequate embeddings for all of those tasks. Finally, we design novel parameter-free probes to justify our hypothesis and demonstrate how attention heads are transformed across the five tasks during MTL through label analysis.",
title={WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit},
author={Yao, Zhuoyuan and Wu, Di and Wang, Xiong and Zhang, Binbin and Yu, Fan and Yang, Chao and Peng, Zhendong and Chen, Xiaoyu and Xie, Lei and Lei, Xin},
