Generalized Parametric Contrastive Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 7463-7474
DOI: 10.1109/tpami.2023.3278694 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Jiequan Cui und 5 weiteren Autor:innen. Die Arbeit wurde bisher 54-mal zitiert (Crossref) und nennt 70 Literaturangaben.
Abstract (Originalsprache)
In this paper, we propose the Generalized Parametric Contrastive Learning (GPaCo/PaCo) which works well on both imbalanced and balanced data. Based on theoretical analysis, we observe supervised contrastive loss tends to bias on high-frequency classes and thus increases the difficulty of imbalanced learning. We introduce a set of parametric class-wise learnable centers to rebalance from an optimization perspective. Further, we analyze our GPaCo/PaCo loss under a balanced setting. Our analysis demonstrates that GPaCo/PaCo can adaptively enhance the intensity of pushing samples of the same class close as more samples are pulled together with their corresponding centers and benefit hard example learning. Experiments on long-tailed benchmarks manifest the new state-of-the-art for long-tailed recognition. On full ImageNet, models from CNNs to vision transformers trained with GPaCo loss show better generalization performance and stronger robustness compared with MAE models. Moreover, GPaCo can be applied to semantic segmentation task and obvious improvements are observed on 4 most popular benchmarks.
Zitieren
APA
Cui, J., Zhong, Z., Tian, Z., Liu, S., Yu, B., & Jia, J. (2024). Generalized Parametric Contrastive Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 7463-7474. https://doi.org/10.1109/tpami.2023.3278694
Vancouver
Cui J, Zhong Z, Tian Z, Liu S, Yu B, Jia J. Generalized Parametric Contrastive Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):7463-7474. doi:10.1109/tpami.2023.3278694
BibTeX
@article{Cui2024,
author = {Cui, Jiequan and Zhong, Zhisheng and Tian, Zhuotao and Liu, Shu and Yu, Bei and Jia, Jiaya},
title = {Generalized Parametric Contrastive Learning},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {12},
pages = {7463--7474},
doi = {10.1109/tpami.2023.3278694}
}
EUVIMED