Unsupervised Semantic Segmentation
51 papers with code • 18 benchmarks • 9 datasets
Models that learn to segment each image (i.e. assign a class to every pixel) without seeing the ground truth labels.
( Image credit: SegSort: Segmentation by Discriminative Sorting of Segments )
Datasets
Most implemented papers
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.
CrOC: Cross-View Online Clustering for Dense Visual Representation Learning
More importantly, the clustering algorithm conjointly operates on the features of both views, thereby elegantly bypassing the issue of content not represented in both views and the ambiguous matching of objects from one crop to the other.
SegSort: Segmentation by Discriminative Sorting of Segments
The proposed SegSort further produces an interpretable result, as each choice of label can be easily understood from the retrieved nearest segments.
Autoregressive Unsupervised Image Segmentation
In this work, we propose a new unsupervised image segmentation approach based on mutual information maximization between different constructed views of the inputs.
Unsupervised Portrait Shadow Removal via Generative Priors
Qualitative and quantitative experiments on a real-world portrait shadow dataset demonstrate that our approach achieves comparable performance with supervised shadow removal methods.
Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement
Firstly, we design an enhancement factor extraction network using depthwise separable convolution for an efficient estimate of the pixel-wise light deficiency of an low-light image.
ViCE: Improving Dense Representation Learning by Superpixelization and Contrasting Cluster Assignment
Recent self-supervised models have demonstrated equal or better performance than supervised methods, opening for AI systems to learn visual representations from practically unlimited data.
Multiple Fusion Adaptation: A Strong Framework for Unsupervised Semantic Segmentation Adaptation
MFA basically considers three parallel information fusion strategies, i. e., the cross-model fusion, temporal fusion and a novel online-offline pseudo label fusion.
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation
Unsupervised semantic segmentation aims to obtain high-level semantic representation on low-level visual features without manual annotations.
Attention-based Transformation from Latent Features to Point Clouds
The points generated by AXform do not have the strong 2-manifold constraint, which improves the generation of non-smooth surfaces.