Decoupled Contrastive Learning for Long-Tailed Recognition
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (6) · 6396-6403
DOI: 10.1609/aaai.v38i6.28459 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Shiyu Xuan und 1 weiteren Autor:innen. Die Arbeit wurde bisher 32-mal zitiert (Crossref).
Abstract (Originalsprache)
Supervised Contrastive Loss (SCL) is popular in visual representation learning. Given an anchor image, SCL pulls two types of positive samples, i.e., its augmentation and other images from the same class together, while pushes negative images apart to optimize the learned embedding. In the scenario of long-tailed recognition, where the number of samples in each class is imbalanced, treating two types of positive samples equally leads to the biased optimization for intra-category distance. In addition, similarity relationship among negative samples, that are ignored by SCL, also presents meaningful semantic cues. To improve the performance on long-tailed recognition, this paper addresses those two issues of SCL by decoupling the training objective. Specifically, it decouples two types of positives in SCL and optimizes their relations toward different objectives to alleviate the influence of the imbalanced dataset. We further propose a patch-based self distillation to transfer knowledge from head to tail classes to relieve the under-representation of tail classes. It uses patch-based features to mine shared visual patterns among different instances and leverages a self distillation procedure to transfer such knowledge. Experiments on different long-tailed classification benchmarks demonstrate the superiority of our method. For instance, it achieves the 57.7% top-1 accuracy on the ImageNet-LT dataset. Combined with the ensemble-based method, the performance can be further boosted to 59.7%, which substantially outperforms many recent works. Our code will be released.
Zitieren
APA
Xuan, S., & Zhang, S. (2024). Decoupled Contrastive Learning for Long-Tailed Recognition. Proceedings of the AAAI Conference on Artificial Intelligence, 38(6), 6396-6403. https://doi.org/10.1609/aaai.v38i6.28459
Vancouver
Xuan S, Zhang S. Decoupled Contrastive Learning for Long-Tailed Recognition. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(6):6396-6403. doi:10.1609/aaai.v38i6.28459
BibTeX
@article{Xuan2024,
author = {Xuan, Shiyu and Zhang, Shiliang},
title = {Decoupled Contrastive Learning for Long-Tailed Recognition},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {6},
pages = {6396--6403},
doi = {10.1609/aaai.v38i6.28459}
}
EUVIMED