Adaptive Semi-Supervised Mixup with Implicit Label Learning and Sample Ratio Balancing
Lists
Only you see this
Abstract
Despite the impressive performance of deep neural networks, they are prone to over-fitting at labeled points rooting from the scarcity of annotated data. Applying mixup regularization in training provides an effective mechanism to improve generalization performance. On the other hand, semi-supervised learning(SSL) leverages an abundant amount of unlabeled data along with a small amount of labeled data in the training process. In this paper, we have introduced mixup regularization to SSL, along with an exploration-utilization training scheme to enhance the performance. Besides, due to the large volume imbalance between labeled/unlabeled data and the unwanted noise resulting from unlabeled samples, we also implement a balancing ratio between the labeled/unlabeled loss terms. Specifically, we devise a novel Sharp Entropy loss for model optimization with large-scale unlabeled samples and employ an uncertainty estimation technique to weigh unlabeled loss function. Extensive experiments show the state-of-the-art performance of SEMixup and uncertainty balancing ratio superior to baselines on image classification.
BibTeX
@inproceedings{su2023adaptive,
author = {Yulin Su and Liangliang Shi and Ziming Feng and Pengzhi Chu and Junchi Yan},
title = {{Adaptive Semi-Supervised Mixup with Implicit Label Learning and Sample Ratio Balancing}},
booktitle = {ICIP},
year = {2023},
url = {https://openreview.net/forum?id=DETKPTOoSn},
}Loading related content...