Semi-Supervised Instance Segmentation
6개 벤치마크 · 논문 20편 · 이 태스크의 논문 보기 →
Benchmarks
COCO 1% labeled data
COCO 10% labeled data
COCO 2% labeled data
COCO 5% labeled data
ADE20K
Cityscapes
Most implemented
CenterMask : Real-Time Anchor-Free Instance Segmentation
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
Boundary-aware Contrastive Learning for Semi-supervised Nuclei Instance Segmentation
Pseudo-label Alignment for Semi-supervised Instance Segmentation
Guided Distillation for Semi-Supervised Instance Segmentation
Papers
StomataSeg: Semi-Supervised Instance Segmentation for Sorghum Stomatal Components
Sorghum is a globally important cereal grown widely in water-limited and stress-prone regions. Its strong drought tolerance makes it a priority crop for climate-resilient agriculture. Improving water-use efficiency in so…
Semi-Supervised Instance SegmentationCAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation
Instance segmentation demands costly per-pixel annotations and large models. We introduce CAST, a semi-supervised knowledge distillation (SSKD) framework that compresses pretrained vision foundation models (VFM) into com…
Domain AdaptationInstance SegmentationKnowledge DistillationPseudo Label+2Pseudo-Label Quality Decoupling and Correction for Semi-Supervised Instance Segmentation
Semi-Supervised Instance Segmentation (SSIS) involves classifying and grouping image pixels into distinct object instances using limited labeled data. This learning paradigm usually faces a significant challenge of unsta…
Instance SegmentationPseudo LabelSemantic SegmentationSemi-Supervised Instance SegmentationS^4M: Boosting Semi-Supervised Instance Segmentation with SAM
Semi-supervised instance segmentation poses challenges due to limited labeled data, causing difficulties in accurately localizing distinct object instances. Current teacher-student frameworks still suffer from performanc…
Data AugmentationInstance SegmentationPseudo LabelSegmentation+2Depth-Guided Semi-Supervised Instance Segmentation
Semi-Supervised Instance Segmentation (SSIS) aims to leverage an amount of unlabeled data during training. Previous frameworks primarily utilized the RGB information of unlabeled images to generate pseudo-labels. However…
Depth EstimationInstance SegmentationSemantic SegmentationSemi-Supervised Instance SegmentationBetter (pseudo-)labels for semi-supervised instance segmentation
Despite the availability of large datasets for tasks like image classification and image-text alignment, labeled data for more complex recognition tasks, such as detection and segmentation, is less abundant. In particula…
Few-Shot Learningimage-classificationImage ClassificationInstance Segmentation+2