Weakly-Supervised Semantic Segmentation
145 papers with code • 9 benchmarks • 8 datasets
The semantic segmentation task is to assign a label from a label set to each pixel in an image. In the case of fully supervised setting, the dataset consists of images and their corresponding pixel-level class-specific annotations (expensive pixel-level annotations). However, in the weakly-supervised setting, the dataset consists of images and corresponding annotations that are relatively easy to obtain, such as tags/labels of objects present in the image.
( Image credit: Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing )
Benchmarks
These leaderboards are used to track progress in Weakly-Supervised Semantic Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Weakly-Supervised Semantic Segmentation models and implementationsDatasets
Cityscapes
ADE20K
PASCAL VOC 2012 test
ScribbleSup
ScribbleKITTI
ACDC Scribbles
CheXlocalize
Most implemented papers
Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation
cvlab-yonsei/BANA
•
•
CVPR 2021
We address the problem of weakly-supervised semantic segmentation (WSSS) using bounding box annotations.
SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds
QingyongHu/SQN
•
•
Labelling point clouds fully is highly time-consuming and costly.
Pseudo-mask Matters in Weakly-supervised Semantic Segmentation
For these matters, we propose the following designs to push the performance to new state-of-art: (i) Coefficient of Variation Smoothing to smooth the CAMs adaptively; (ii) Proportional Pseudo-mask Generation to project the expanded CAMs to pseudo-mask based on a new metric indicating the importance of each class on each location, instead of the scores trained from binary classifiers.
Adaptive Early-Learning Correction for Segmentation from Noisy Annotations
kangningthu/adele
•
•
CVPR 2022
We discover a phenomenon that has been previously reported in the context of classification: the networks tend to first fit the clean pixel-level labels during an "early-learning" phase, before eventually memorizing the false annotations.
Cross Language Image Matching for Weakly Supervised Semantic Segmentation
cvi-szu/clims
•
•
As only a fixed set of image-level object labels are available to the WSSS (weakly supervised semantic segmentation) model, it could be very difficult to suppress those diverse background regions consisting of open set objects.
RecurSeed and EdgePredictMix: Pseudo-Label Refinement Learning for Weakly Supervised Semantic Segmentation across Single- and Multi-Stage Frameworks
shjo-april/recurseed_and_edgepredictmix
•
•
Although weakly supervised semantic segmentation using only image-level labels (WSSS-IL) is potentially useful, its low performance and implementation complexity still limit its application.
ReFit: A Framework for Refinement of Weakly Supervised Semantic Segmentation using Object Border Fitting for Medical Images
Weakly Supervised Semantic Segmentation (WSSS) relying only on image-level supervision is a promising approach to deal with the need for Segmentation networks, especially for generating a large number of pixel-wise masks in a given dataset.
Prompting classes: Exploring the Power of Prompt Class Learning in Weakly Supervised Semantic Segmentation
First, modifying only the class token of the text prompt results in a greater impact on the Class Activation Map (CAM), compared to arguably more complex strategies that optimize the context.
Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation
In addition, our method also achieves state-of-the-art weakly supervised semantic segmentation performance on the PASCAL VOC 2012 and MS COCO 2014 datasets.
Learning without Exact Guidance: Updating Large-scale High-resolution Land Cover Maps from Low-resolution Historical Labels
However, it is still a non-trivial task hindered by complex ground details, various landforms, and the scarcity of accurate training labels over a wide-span geographic area.
