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
Tackling Ambiguity from Perspective of Uncertainty Inference and Affinity Diversification for Weakly Supervised Semantic Segmentation
When activating class objects, we argue that the false activation stems from the bias to the ambiguous regions during the feature extraction.
Fully Convolutional Multi-Class Multiple Instance Learning
We propose a novel MIL formulation of multi-class semantic segmentation learning by a fully convolutional network.
STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
shimoda-uec/ssdd
•
•
Then, a better network called Enhanced-DCNN is learned with supervision from the predicted segmentation masks of simple images based on the Initial-DCNN as well as the image-level annotations.
Spatio-temporal video autoencoder with differentiable memory
At each time step, the system receives as input a video frame, predicts the optical flow based on the current observation and the LSTM memory state as a dense transformation map, and applies it to the current frame to generate the next frame.
Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation
arslan-chaudhry/dcsp_segmentation
•
•
We propose an approach to discover class-specific pixels for the weakly-supervised semantic segmentation task.
Learning to Exploit the Prior Network Knowledge for Weakly-Supervised Semantic Segmentation
Training a Convolutional Neural Network (CNN) for semantic segmentation typically requires to collect a large amount of accurate pixel-level annotations, a hard and expensive task.
Bootstrapping the Performance of Webly Supervised Semantic Segmentation
In this work, we focus on weak supervision, developing a method for training a high-quality pixel-level classifier for semantic segmentation, using only image-level class labels as the provided ground-truth.
Weakly-Supervised Semantic Segmentation Network With Deep Seeded Region Growing
speedinghzl/DSRG
•
•
CVPR 2018
Inspired by the traditional image segmentation methods of seeded region growing, we propose to train a semantic segmentation network starting from the discriminative regions and progressively increase the pixel-level supervision using by seeded region growing.
Convolutional Simplex Projection Network (CSPN) for Weakly Supervised Semantic Segmentation
briqr/CSPN
•
•
Weakly supervised semantic segmentation has been a subject of increased interest due to the scarcity of fully annotated images.
Weakly- and Semi-Supervised Panoptic Segmentation
We present a weakly supervised model that jointly performs both semantic- and instance-segmentation -- a particularly relevant problem given the substantial cost of obtaining pixel-perfect annotation for these tasks.
