Revisiting Consistency Regularization for Semi-Supervised Learning
Consistency regularization is one of the most widely-used techniques for semi-supervised learning (SSL). Generally, the aim is to train a model that is invariant to various data augmentations. In this paper, we revisit this idea and find that enforcing invariance by decreasing distances between features from differently augmented images leads to improved performance. However, encouraging equivariance instead, by increasing the feature distance, further improves performance. To this end, we propose an improved consistency regularization framework by a simple yet effective technique, FeatDistLoss, that imposes consistency and equivariance on the classifier and the feature level, respectively. Experimental results show that our model defines a new state of the art for various datasets and settings and outperforms previous work by a significant margin, particularly in low data regimes. Extensive experiments are conducted to analyze the method, and the code will be published.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Revisiting Network Perturbation for Semi-Supervised Semantic Segmentation
In semi-supervised semantic segmentation (SSS), weak-to-strong consistency regularization techniques are widely utilized in recent works, typically combined with input-level and feature-level perturbations. However, the …
Semantic SegmentationSemi-Supervised Semantic SegmentationSupercm: Revisiting Clustering for Semi-Supervised Learning
The development of semi-supervised learning (SSL) has in recent years largely focused on the development of new consistency regularization or entropy minimization approaches, often resulting in models with complex traini…
ClusteringRevisiting CycleGAN for semi-supervised segmentation
In this work, we study the problem of training deep networks for semantic image segmentation using only a fraction of annotated images, which may significantly reduce human annotation efforts. Particularly, we propose a …
Image SegmentationSegmentationSemantic SegmentationStyle TransferSemi-Supervised Learning with GANs: Revisiting Manifold Regularization
GANS are powerful generative models that are able to model the manifold of natural images. We leverage this property to perform manifold regularization by approximating the Laplacian norm using a Monte Carlo approximatio…
Region-level Contrastive and Consistency Learning for Semi-Supervised Semantic Segmentation
Current semi-supervised semantic segmentation methods mainly focus on designing pixel-level consistency and contrastive regularization. However, pixel-level regularization is sensitive to noise from pixels with incorrect…
SegmentationSemantic SegmentationSemi-Supervised Semantic Segmentation