Revisit Overconfidence for OOD Detection: Reassigned Contrastive Learning with Adaptive Class-dependent Threshold

Yanan Wu, Keqing He, Yuanmeng Yan, QiXiang Gao, Zhiyuan Zeng, Fujia Zheng, Lulu Zhao, Huixing Jiang, Wei Wu, Weiran Xu. Revisit Overconfidence for OOD Detection: Reassigned Contrastive Learning with Adaptive Class-dependent Threshold. In Marine Carpuat, Marie-Catherine de Marneffe, Iván Vladimir Meza Ruíz, editors, Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022, Seattle, WA, United States, July 10-15, 2022. pages 4165-4179, Association for Computational Linguistics, 2022. [doi]

@inproceedings{WuHYGZZZJWX22,
  title = {Revisit Overconfidence for OOD Detection: Reassigned Contrastive Learning with Adaptive Class-dependent Threshold},
  author = {Yanan Wu and Keqing He and Yuanmeng Yan and QiXiang Gao and Zhiyuan Zeng and Fujia Zheng and Lulu Zhao and Huixing Jiang and Wei Wu and Weiran Xu},
  year = {2022},
  url = {https://aclanthology.org/2022.naacl-main.307},
  researchr = {https://researchr.org/publication/WuHYGZZZJWX22},
  cites = {0},
  citedby = {0},
  pages = {4165-4179},
  booktitle = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022, Seattle, WA, United States, July 10-15, 2022},
  editor = {Marine Carpuat and Marie-Catherine de Marneffe and Iván Vladimir Meza Ruíz},
  publisher = {Association for Computational Linguistics},
  isbn = {978-1-955917-71-1},
}