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

Most implemented papers

Most implemented Social Latest No code

Universal Semi-Supervised Semantic Segmentation

tarun005/USSS_ICCV19 • • ICCV 2019

In recent years, the need for semantic segmentation has arisen across several different applications and environments.

1
Paper
Code

Curriculum semi-supervised segmentation

LIVIAETS/semi_curriculum • • 10 Apr 2019

This study investigates a curriculum-style strategy for semi-supervised CNN segmentation, which devises a regression network to learn image-level information such as the size of a target region.

1
Paper
Code

Semi-Supervised Semantic Segmentation with High- and Low-level Consistency

sud0301/semisup-semseg • • 15 Aug 2019

The ability to understand visual information from limited labeled data is an important aspect of machine learning.

1
Paper
Code

Saliency Guided Self-attention Network for Weakly and Semi-supervised Semantic Segmentation

yaoqi-zd/SGAN • • 12 Oct 2019

Weakly supervised semantic segmentation (WSSS) using only image-level labels can greatly reduce the annotation cost and therefore has attracted considerable research interest.

1
Paper
Code

DMT: Dynamic Mutual Training for Semi-Supervised Learning

voldemortX/DST-CBC • • 18 Apr 2020

Instead, leveraging inter-model disagreement between different models is a key to locate pseudo label errors.

1
Paper
Code

Learning High-Resolution Domain-Specific Representations with a GAN Generator

saic-vul/GAN-high-resolution-representation • • 18 Jun 2020

Based on this finding, we propose LayerMatch scheme for approximating the representation of a GAN generator that can be used for unsupervised domain-specific pretraining.

1
Paper
Code

Guided Collaborative Training for Pixel-wise Semi-Supervised Learning

ZHKKKe/PixelSSL • • ECCV 2020

Although SSL methods have achieved impressive results in image classification, the performances of applying them to pixel-wise tasks are unsatisfactory due to their need for dense outputs.

1
Paper
Code

A Three-Stage Self-Training Framework for Semi-Supervised Semantic Segmentation

RK621/ThreeStageSelftraining_SemanticSegmentation • • 1 Dec 2020

The key idea of our technique is the extraction of the pseudo-masks statistical information to decrease uncertainty in the predicted probability whilst enforcing segmentation consistency in a multi-task fashion.

1
Paper
Code

Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation

lhoyer/improving_segmentation_with_selfsupervised_depth • • CVPR 2021

Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process.

1
Paper
Code

Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation

jbeomlee93/AdvCAM • • CVPR 2021

Weakly supervised semantic segmentation produces a pixel-level localization from a classifier, but it is likely to restrict its focus to a small discriminative region of the target object.

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