Computer Vision
 
Edit

Semi-Supervised Semantic Segmentation

88 papers with code • 45 benchmarks • 12 datasets

Models that are trained with a small number of labeled examples and a large number of unlabeled examples and whose aim is to learn to segment an image (i.e. assign a class to every pixel).

Libraries

Use these libraries to find Semi-Supervised Semantic Segmentation models and implementations
HiLab-git/SSL4MIS
3 papers
1,984
harshm121/m3l
2 papers
28

Datasets

Most implemented papers

Most implemented Social Latest No code

PseudoSeg: Designing Pseudo Labels for Semantic Segmentation

googleinterns/wss • • ICLR 2021

We demonstrate the effectiveness of the proposed pseudo-labeling strategy in both low-data and high-data regimes.

2
Paper
Code

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation

xinge008/Cylinder3D • • CVPR 2021

However, we found that in the outdoor point cloud, the improvement obtained in this way is quite limited.

2
Paper
Code

Bootstrapping Semantic Segmentation with Regional Contrast

lorenmt/reco • • ICLR 2022

We present ReCo, a contrastive learning framework designed at a regional level to assist learning in semantic segmentation.

2
Paper
Code

Semi-supervised Semantic Segmentation with Directional Context-aware Consistency

dvlab-research/Context-Aware-Consistency • • CVPR 2021

Semantic segmentation has made tremendous progress in recent years.

2
Paper
Code

LaserMix for Semi-Supervised LiDAR Semantic Segmentation

ldkong1205/LaserMix • • CVPR 2023

Densely annotating LiDAR point clouds is costly, which restrains the scalability of fully-supervised learning methods.

2
Paper
Code

Triple-View Feature Learning for Medical Image Segmentation

HiLab-git/SSL4MIS • • 12 Aug 2022

The confidence of each model gets improved through the other two views of the feature learning.

2
Paper
Code

Pseudo-Label Guided Contrastive Learning for Semi-Supervised Medical Image Segmentation

HiLab-git/SSL4MIS • • CVPR 2023

Although recent works in semi-supervised learning (SemiSL) have accomplished significant success in natural image segmentation, the task of learning discriminative representations from limited annotations has been an open problem in medical images.

2
Paper
Code

Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation

HiLab-git/SSL4MIS • • CVPR 2023

In semi-supervised medical image segmentation, there exist empirical mismatch problems between labeled and unlabeled data distribution.

2
Paper
Code

Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training

yzou2/CBST • • ECCV 2018

Recent deep networks achieved state of the art performanceon a variety of semantic segmentation tasks.

1
Paper
Code

Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning

arnab39/FewShot_GAN-Unet3D • • 29 Oct 2018

In addition, our work presents a comprehensive analysis of different GAN architectures for semi-supervised segmentation, showing recent techniques like feature matching to yield a higher performance than conventional adversarial training approaches.

1
Paper
Code
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy