Unsupervised Semantic Segmentation
52 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 )
Benchmarks
These leaderboards are used to track progress in Unsupervised Semantic Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Datasets
MS COCO
Cityscapes
COCO-Stuff
Dark Zurich
ImageNet-S
SUIM
Nighttime Driving
ACDC (Adverse Conditions Dataset with Correspondences)
KITTI-STEP
Most implemented papers
Disentangled Latent Transformer for Interpretable Monocular Height Estimation
shadowxzt/dlt-height-estimation.pytorch
•
•
Furthermore, a novel unsupervised semantic segmentation task based on height estimation is first introduced in this work.
Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation
This work investigates learning pixel-wise semantic image segmentation in urban scenes without any manual annotation, just from the raw non-curated data collected by cars which, equipped with cameras and LiDAR sensors, drive around a city.
Dense Siamese Network for Dense Unsupervised Learning
It also extracts a batch of region embeddings that correspond to some sub-regions in the overlapped area to be contrasted for region consistency.
Unsupervised Hierarchical Semantic Segmentation with Multiview Cosegmentation and Clustering Transformers
twke18/hsg
•
•
CVPR 2022
We enforce spatial consistency of grouping and bootstrap feature learning with co-segmentation among multiple views of the same image, and enforce semantic consistency across the grouping hierarchy with clustering transformers between coarse- and fine-grained features.
Self-Supervised Learning of Object Parts for Semantic Segmentation
mkuuwaujinga/leopart
•
•
CVPR 2022
However, learning dense representations is challenging, as in the unsupervised context it is not clear how to guide the model to learn representations that correspond to various potential object categories.
Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization
lukemelas/deep-spectral-segmentation
•
•
CVPR 2022
We find that these eigenvectors already decompose an image into meaningful segments, and can be readily used to localize objects in a scene.
Self-Supervised Visual Representation Learning with Semantic Grouping
CVMI-Lab/SlotCon
•
•
The semantic grouping is performed by assigning pixels to a set of learnable prototypes, which can adapt to each sample by attentive pooling over the feature and form new slots.
SERE: Exploring Feature Self-relation for Self-supervised Transformer
MCG-NKU/SERE
•
•
Specifically, instead of conducting self-supervised learning solely on feature embeddings from multiple views, we utilize the feature self-relations, i. e., spatial/channel self-relations, for self-supervised learning.
Discovering Object Masks with Transformers for Unsupervised Semantic Segmentation
This paper presents MaskDistill: a novel framework for unsupervised semantic segmentation based on three key ideas.
Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations
In this paper, we show that recent advances in self-supervised feature learning enable unsupervised object discovery and semantic segmentation with a performance that matches the state of the field on supervised semantic segmentation 10 years ago.
