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
1,999
harshm121/m3l
2 papers
30

Datasets

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.

1,999
01 May 2023
Paper
Code

Semi-Supervised Semantic Segmentation With Region Relevance

nust-machine-intelligence-laboratory/torchsemiseg2 • • 23 Apr 2023

The most common approach is to generate pseudo-labels for unlabeled images to augment the training data.

1
23 Apr 2023
Paper
Code

Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentation

harshm121/m3l • • 21 Apr 2023

We create the first benchmark for semi-supervised multi-modal semantic segmentation and also report the robustness to missing modalities.

30
21 Apr 2023
Paper
Code

CAFS: Class Adaptive Framework for Semi-Supervised Semantic Segmentation

cjf8899/cafs • • 21 Mar 2023

Unlike existing semi-supervised semantic segmentation frameworks, CAFS constructs a validation set on a labeled dataset, to leverage the calibration performance for each class.

9
21 Mar 2023
Paper
Code

Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation

l1997i/lim3d • • CVPR 2023

Whilst the availability of 3D LiDAR point cloud data has significantly grown in recent years, annotation remains expensive and time-consuming, leading to a demand for semi-supervised semantic segmentation methods with application domains such as autonomous driving.

79
20 Mar 2023
Paper
Code

SpiderMesh: Spatial-aware Demand-guided Recursive Meshing for RGB-T Semantic Segmentation

leofansq/spidermesh • • 15 Mar 2023

For semantic segmentation in urban scene understanding, RGB cameras alone often fail to capture a clear holistic topology in challenging lighting conditions.

7
15 Mar 2023
Paper
Code

Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation

xiaoyao3302/CCVC • • CVPR 2023

In this work, we propose a new conflict-based cross-view consistency (CCVC) method based on a two-branch co-training framework which aims at enforcing the two sub-nets to learn informative features from irrelevant views.

42
02 Mar 2023
Paper
Code

Iterative Loop Method Combining Active and Semi-Supervised Learning for Domain Adaptive Semantic Segmentation

licongguan/ilm-assl • • 31 Jan 2023

The method first uses semi-supervised to learn massive unlabeled data to improve model accuracy and provide more accurate selection models for active learning.

32
31 Jan 2023
Paper
Code

Semi-Supervised Semantic Segmentation via Gentle Teaching Assistant

Jin-Ying/GTA-Seg • • NIPS 2022

Semi-Supervised Semantic Segmentation aims at training the segmentation model with limited labeled data and a large amount of unlabeled data.

31
18 Jan 2023
Paper
Code

Co-training with High-Confidence Pseudo Labels for Semi-supervised Medical Image Segmentation

senyh/ucmt • • 11 Jan 2023

Combining the strengths of UMIX with CMT, UCMT can retain model disagreement and enhance the quality of pseudo labels for the co-training segmentation.

26
11 Jan 2023
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