LayerMatch: Do Pseudo-labels Benefit All Layers?
- URL: http://arxiv.org/abs/2406.14207v3
- Date: Thu, 27 Jun 2024 07:01:27 GMT
- Title: LayerMatch: Do Pseudo-labels Benefit All Layers?
- Authors: Chaoqi Liang, Guanglei Yang, Lifeng Qiao, Zitong Huang, Hongliang Yan, Yunchao Wei, Wangmeng Zuo,
- Abstract summary: Semi-supervised learning offers a promising solution to mitigate the dependency of labeled data.
We develop two layer-specific pseudo-label strategies, termed Grad-ReLU and Avg-Clustering.
Our approach consistently demonstrates exceptional performance on standard semi-supervised learning benchmarks.
- Score: 77.59625180366115
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Deep neural networks have achieved remarkable performance across various tasks when supplied with large-scale labeled data. However, the collection of labeled data can be time-consuming and labor-intensive. Semi-supervised learning (SSL), particularly through pseudo-labeling algorithms that iteratively assign pseudo-labels for self-training, offers a promising solution to mitigate the dependency of labeled data. Previous research generally applies a uniform pseudo-labeling strategy across all model layers, assuming that pseudo-labels exert uniform influence throughout. Contrasting this, our theoretical analysis and empirical experiment demonstrate feature extraction layer and linear classification layer have distinct learning behaviors in response to pseudo-labels. Based on these insights, we develop two layer-specific pseudo-label strategies, termed Grad-ReLU and Avg-Clustering. Grad-ReLU mitigates the impact of noisy pseudo-labels by removing the gradient detrimental effects of pseudo-labels in the linear classification layer. Avg-Clustering accelerates the convergence of feature extraction layer towards stable clustering centers by integrating consistent outputs. Our approach, LayerMatch, which integrates these two strategies, can avoid the severe interference of noisy pseudo-labels in the linear classification layer while accelerating the clustering capability of the feature extraction layer. Through extensive experimentation, our approach consistently demonstrates exceptional performance on standard semi-supervised learning benchmarks, achieving a significant improvement of 10.38% over baseline method and a 2.44% increase compared to state-of-the-art methods.
Related papers
- Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning [81.83013974171364]
Semi-supervised multi-label learning (SSMLL) is a powerful framework for leveraging unlabeled data to reduce the expensive cost of collecting precise multi-label annotations.
Unlike semi-supervised learning, one cannot select the most probable label as the pseudo-label in SSMLL due to multiple semantics contained in an instance.
We propose a dual-perspective method to generate high-quality pseudo-labels.
arXiv Detail & Related papers (2024-07-26T09:33:53Z) - AllMatch: Exploiting All Unlabeled Data for Semi-Supervised Learning [5.0823084858349485]
We present a novel SSL algorithm named AllMatch, which achieves improved pseudo-label accuracy and a 100% utilization ratio for the unlabeled data.
The results demonstrate that AllMatch consistently outperforms existing state-of-the-art methods.
arXiv Detail & Related papers (2024-06-22T06:59:52Z) - TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary
Multi-Label Classification of CLIP Without Training [29.431698321195814]
Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in open-vocabulary classification.
CLIP shows poor performance on multi-label datasets because the global feature tends to be dominated by the most prominent class.
We propose a local-to-global framework to obtain image tags.
arXiv Detail & Related papers (2023-12-20T08:15:40Z) - PercentMatch: Percentile-based Dynamic Thresholding for Multi-Label
Semi-Supervised Classification [64.39761523935613]
We propose a percentile-based threshold adjusting scheme to dynamically alter the score thresholds of positive and negative pseudo-labels for each class during the training.
We achieve strong performance on Pascal VOC2007 and MS-COCO datasets when compared to recent SSL methods.
arXiv Detail & Related papers (2022-08-30T01:27:48Z) - Transductive CLIP with Class-Conditional Contrastive Learning [68.51078382124331]
We propose Transductive CLIP, a novel framework for learning a classification network with noisy labels from scratch.
A class-conditional contrastive learning mechanism is proposed to mitigate the reliance on pseudo labels.
ensemble labels is adopted as a pseudo label updating strategy to stabilize the training of deep neural networks with noisy labels.
arXiv Detail & Related papers (2022-06-13T14:04:57Z) - Contrastive Regularization for Semi-Supervised Learning [46.020125061295886]
We propose contrastive regularization to improve both efficiency and accuracy of the consistency regularization by well-clustered features of unlabeled data.
Our method also shows robust performance on open-set semi-supervised learning where unlabeled data includes out-of-distribution samples.
arXiv Detail & Related papers (2022-01-17T07:20:11Z) - Rethinking Pseudo Labels for Semi-Supervised Object Detection [84.697097472401]
We introduce certainty-aware pseudo labels tailored for object detection.
We dynamically adjust the thresholds used to generate pseudo labels and reweight loss functions for each category to alleviate the class imbalance problem.
Our approach improves supervised baselines by up to 10% AP using only 1-10% labeled data from COCO.
arXiv Detail & Related papers (2021-06-01T01:32:03Z) - PseudoSeg: Designing Pseudo Labels for Semantic Segmentation [78.35515004654553]
We present a re-design of pseudo-labeling to generate structured pseudo labels for training with unlabeled or weakly-labeled data.
We demonstrate the effectiveness of the proposed pseudo-labeling strategy in both low-data and high-data regimes.
arXiv Detail & Related papers (2020-10-19T17:59:30Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.