Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation
We present a novel semi-supervised semantic segmentation method which jointly achieves two desiderata of segmentation model regularities: the label-space consistency property between image augmentations and the feature-space contrastive property among different pixels. We leverage the pixel-level L2 loss and the pixel contrastive loss for the two purposes respectively. To address the computational efficiency issue and the false negative noise issue involved in the pixel contrastive loss, we further introduce and investigate several negative sampling techniques. Extensive experiments demonstrate the state-of-the-art performance of our method (PC2Seg) with the DeepLab-v3+ architecture, in several challenging semi-supervised settings derived from the VOC, Cityscapes, and COCO datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Computational EfficiencySegmentationSemantic SegmentationSemi-Supervised Semantic SegmentationSimilar Papers 제목 키워드 기반
Bootstrapping Semantic Segmentation with Regional Contrast
We present ReCo, a contrastive learning framework designed at a regional level to assist learning in semantic segmentation. ReCo performs semi-supervised or supervised pixel-level contrastive learning on a sparse set of …
Contrastive LearningSegmentationSemantic SegmentationSemi-Supervised Semantic SegmentationRegion-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 SegmentationSemi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank
This work presents a novel approach for semi-supervised semantic segmentation. The key element of this approach is our contrastive learning module that enforces the segmentation network to yield similar pixel-level featu…
Contrastive LearningDomain AdaptationRepresentation LearningSegmentation+3C3-SemiSeg: Contrastive Semi-Supervised Segmentation via Cross-Set Learning and Dynamic Class-Balancing
The semi-supervised semantic segmentation methods utilize the unlabeled data to increase the feature discriminative ability to alleviate the burden of the annotated data. However, the dominant consistency learning di…
Contrastive LearningData AugmentationSemantic SegmentationSemi-Supervised Semantic SegmentationLooking Beyond Single Images for Contrastive Semantic Segmentation Learning
We present an approach to contrastive representation learning for semantic segmentation. Our approach leverages the representational power of existing feature extractors to find corresponding regions across images. These…
Contrastive Learningimage-classificationImage ClassificationRepresentation Learning+3