Rain&Bus
11953eef67
LaTeX Build / build (push) Canceled after 0s
Paper draft for the second work (thesis Ch.4 ZGDPE, renamed DZGCoOp): abstract, intro, related work, method (zero-shot guidance module, asymmetric dual-branch with deep prompts, confidence-guided dynamic fusion, guidance losses + EWA), experiments (base-to-novel, cross-domain, cross-dataset, ablations) and conclusion. Compiles to 8 pages with tectonic (no errors, no overfull boxes).
159 lines
6.4 KiB
BibTeX
159 lines
6.4 KiB
BibTeX
% References for the DZGCoOp paper.
|
|
% Full-form entries, no string abbreviations.
|
|
|
|
@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 Krueger, Gretchen and Sutskever, Ilya},
|
|
booktitle={Proceedings of the International Conference on Machine Learning},
|
|
pages={8748--8763},
|
|
year={2021}
|
|
}
|
|
|
|
@inproceedings{jia2021scaling,
|
|
title={Scaling up visual and vision-language representation learning with noisy text supervision},
|
|
author={Jia, Chao and Yang, Yinfei and Xia, Ye and Chen, Yi-Ting and Parekh, Zarana and Pham, Hieu and Le, Quoc and Sung, Yun-Hsuan and Li, Zhen and Duerig, Tom},
|
|
booktitle={Proceedings of the International Conference on Machine Learning},
|
|
pages={4904--4916},
|
|
year={2021}
|
|
}
|
|
|
|
@article{zhou2022learning,
|
|
title={Learning to prompt for vision-language models},
|
|
author={Zhou, Kaiyang and Yang, Jingkang and Loy, Chen Change and Liu, Ziwei},
|
|
journal={International Journal of Computer Vision},
|
|
volume={130},
|
|
number={9},
|
|
pages={2337--2348},
|
|
year={2022}
|
|
}
|
|
|
|
@inproceedings{zhou2022conditional,
|
|
title={Conditional prompt learning for vision-language models},
|
|
author={Zhou, Kaiyang and Yang, Jingkang and Loy, Chen Change and Liu, Ziwei},
|
|
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
|
|
pages={16816--16825},
|
|
year={2022}
|
|
}
|
|
|
|
@inproceedings{yao2023visual,
|
|
title={Visual-language prompt tuning with knowledge-guided context optimization},
|
|
author={Yao, Hantao and Zhang, Rui and Xu, Changsheng},
|
|
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
|
|
pages={6757--6767},
|
|
year={2023}
|
|
}
|
|
|
|
@inproceedings{khattak2023maple,
|
|
title={MaPLe: Multi-modal prompt learning},
|
|
author={Khattak, Muhammad Uzair and Rasheed, Hanoona and Maaz, Muhammad and Khan, Salman and Khan, Fahad Shahbaz},
|
|
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
|
|
pages={19113--19122},
|
|
year={2023}
|
|
}
|
|
|
|
@inproceedings{kim2024aapl,
|
|
title={AAPL: Adding attributes to prompt learning for vision-language models},
|
|
author={Kim, Gahyeon and Kim, Sohee and Lee, Seokju},
|
|
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
|
|
pages={1572--1582},
|
|
year={2024}
|
|
}
|
|
|
|
@inproceedings{zhu2023prompt,
|
|
title={Prompt-aligned gradient for prompt tuning},
|
|
author={Zhu, Beier and Niu, Yulei and Han, Yucheng and Wu, Yue and Zhang, Hanwang},
|
|
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
|
|
pages={15659--15669},
|
|
year={2023}
|
|
}
|
|
|
|
@inproceedings{jia2022visual,
|
|
title={Visual prompt tuning},
|
|
author={Jia, Menglin and Tang, Luming and Chen, Bor-Chun and Cardie, Claire and Belongie, Serge and Hariharan, Bharath and Lim, Ser-Nam},
|
|
booktitle={European Conference on Computer Vision},
|
|
pages={709--727},
|
|
year={2022}
|
|
}
|
|
|
|
@inproceedings{izmailov2018averaging,
|
|
title={Averaging weights leads to wider optima and better generalization},
|
|
author={Izmailov, Pavel and Podoprikhin, Dmitrii and Garipov, Timur and Vetrov, Dmitry P. and Wilson, Andrew Gordon},
|
|
booktitle={Proceedings of the Conference on Uncertainty in Artificial Intelligence},
|
|
pages={876--885},
|
|
year={2018}
|
|
}
|
|
|
|
@article{kullback1951information,
|
|
title={On information and sufficiency},
|
|
author={Kullback, Solomon and Leibler, Richard A.},
|
|
journal={The Annals of Mathematical Statistics},
|
|
volume={22},
|
|
number={1},
|
|
pages={79--86},
|
|
year={1951}
|
|
}
|
|
|
|
@inproceedings{deng2009imagenet,
|
|
title={ImageNet: A large-scale hierarchical image database},
|
|
author={Deng, Jia and Dong, Wei and Socher, Richard and Li, Li-Jia and Li, Kai and Fei-Fei, Li},
|
|
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
|
|
pages={248--255},
|
|
year={2009}
|
|
}
|
|
|
|
@inproceedings{recht2019imagenet,
|
|
title={Do ImageNet classifiers generalize to ImageNet?},
|
|
author={Recht, Benjamin and Roelofs, Rebecca and Schmidt, Ludwig and Shankar, Vaishaal},
|
|
booktitle={Proceedings of the International Conference on Machine Learning},
|
|
pages={5389--5400},
|
|
year={2019}
|
|
}
|
|
|
|
@inproceedings{wang2019learning,
|
|
title={Learning robust global representations by penalizing local predictive power},
|
|
author={Wang, Haohan and Ge, Songwei and Lipton, Zachary and Xing, Eric P.},
|
|
booktitle={Advances in Neural Information Processing Systems},
|
|
volume={32},
|
|
year={2019}
|
|
}
|
|
|
|
@inproceedings{hendrycks2021natural,
|
|
title={Natural adversarial examples},
|
|
author={Hendrycks, Dan and Zhao, Kevin and Basart, Steven and Steinhardt, Jacob and Song, Dawn},
|
|
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
|
|
pages={15262--15271},
|
|
year={2021}
|
|
}
|
|
|
|
@inproceedings{hendrycks2021many,
|
|
title={The many faces of robustness: A critical analysis of out-of-distribution generalization},
|
|
author={Hendrycks, Dan and Basart, Steven and Mu, Norman and Kadavath, Saurav and Wang, Frank and Dorundo, Evan and Desai, Rahul and Zhu, Tyler and Parajuli, Samyak and Guo, Mike and Song, Dawn and Steinhardt, Jacob and Gilmer, Justin},
|
|
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
|
|
pages={8340--8349},
|
|
year={2021}
|
|
}
|
|
|
|
@inproceedings{brown2020language,
|
|
title={Language models are few-shot learners},
|
|
author={Brown, Tom and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared D. and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and Agarwal, Sandhini and others},
|
|
booktitle={Advances in Neural Information Processing Systems},
|
|
volume={33},
|
|
pages={1877--1901},
|
|
year={2020}
|
|
}
|
|
|
|
@article{achiam2023gpt,
|
|
title={GPT-4 technical report},
|
|
author={Achiam, Josh and Adler, Steven and Agarwal, Sandhini and Ahmad, Lama and Akkaya, Ilge and Altman, Florencia Leoni and Almeida, Diogo and Altenschmidt, Max and Altman, Sam and Anadkat, Shyamal and others},
|
|
journal={arXiv preprint arXiv:2303.08774},
|
|
year={2023}
|
|
}
|
|
|
|
% TODO: update the venue/status of our first work (MSGCoOp) before submission.
|
|
@article{wang2025msgcoop,
|
|
title={{MSGCoOp}: Multiple semantic-guided context optimization for few-shot learning},
|
|
author={Wang, Zhaolong and Sun, Tongfeng and Du, Mingzheng and Huang, Yachao and Xu, Xinzheng and Li, Zhongnian},
|
|
journal={arXiv preprint arXiv:XXXX.XXXXX},
|
|
year={2025}
|
|
}
|