paper-with-me

Semi-Supervised Instance Segmentation

6개 벤치마크 · 논문 20편 · 이 태스크의 논문 보기 →

Benchmarks

COCO 1% labeled data

결과 3개

COCO 10% labeled data

결과 3개

COCO 2% labeled data

결과 3개

COCO 5% labeled data

결과 3개

ADE20K

결과 1개

Cityscapes

결과 1개

Most implemented

Papers

StomataSeg: Semi-Supervised Instance Segmentation for Sorghum Stomatal Components

2026-01-31 · Zhongtian Huang, Zhi Chen, Zi Huang, Xin Yu 외 arxiv

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 Segmentation

CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation

2025-05-28 · Pardis Taghavi, Tian Liu, Renjie Li, Reza Langari 외

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+2

Pseudo-Label Quality Decoupling and Correction for Semi-Supervised Instance Segmentation

2025-05-16 · Jianghang Lin, Yilin Lu, Yunhang Shen, Chaoyang Zhu 외

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 Segmentation

S^4M: Boosting Semi-Supervised Instance Segmentation with SAM

2025-04-07 · Heeji Yoon, Heeseong Shin, Eunbeen Hong, Hyunwook Choi 외

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+2

Depth-Guided Semi-Supervised Instance Segmentation

2024-06-25 · Xin Chen, Jie Hu, Xiawu Zheng, Jianghang Lin 외

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 Segmentation

Better (pseudo-)labels for semi-supervised instance segmentation

2024-03-18 · François Porcher, Camille Couprie, Marc Szafraniec, Jakob Verbeek

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

전체 20편 보기 →