Beyond Pixels: Semi-Supervised Semantic Segmentation with a Multi-scale Patch-based Multi-Label Classifier
Incorporating pixel contextual information is critical for accurate segmentation. In this paper, we show that an effective way to incorporate contextual information is through a patch-based classifier. This patch classifier is trained to identify classes present within an image region, which facilitates the elimination of distractors and enhances the classification of small object segments. Specifically, we introduce Multi-scale Patch-based Multi-label Classifier (MPMC), a novel plug-in module designed for existing semi-supervised segmentation (SSS) frameworks. MPMC offers patch-level supervision, enabling the discrimination of pixel regions of different classes within a patch. Furthermore, MPMC learns an adaptive pseudo-label weight, using patch-level classification to alleviate the impact of the teacher's noisy pseudo-label supervision the student. This lightweight module can be integrated into any SSS framework, significantly enhancing their performance. We demonstrate the efficacy of our proposed MPMC by integrating it into four SSS methodologies and improving them across two natural image and one medical segmentation dataset, notably improving the segmentation results of the baselines across all the three datasets.
Code (2)
Tasks
Pseudo LabelSegmentationSemantic SegmentationSemi-Supervised Semantic SegmentationSimilar Papers 제목 키워드 기반
CAFS: Class Adaptive Framework for Semi-Supervised Semantic Segmentation
Semi-supervised semantic segmentation learns a model for classifying pixels into specific classes using a few labeled samples and numerous unlabeled images. The recent leading approach is consistency regularization by se…
SegmentationSemantic SegmentationSemi-Supervised Semantic SegmentationBootstrapping 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 SegmentationWeighting Pseudo-Labels via High-Activation Feature Index Similarity and Object Detection for Semi-Supervised Segmentation
Semi-supervised semantic segmentation methods leverage unlabeled data by pseudo-labeling them. Thus the success of these methods hinges on the reliablility of the pseudo-labels. Existing methods mostly choose high-confid…
object-detectionObject DetectionPseudo LabelSegmentation+2Semi-Supervised Semantic Segmentation via Marginal Contextual Information
We present a novel confidence refinement scheme that enhances pseudo labels in semi-supervised semantic segmentation. Unlike existing methods, which filter pixels with low-confidence predictions in isolation, our approac…
SegmentationSemantic 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 Segmentation