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 )
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
Latest papers with no code
OMH: Structured Sparsity via Optimally Matched Hierarchy for Unsupervised Semantic Segmentation
Our OMH yields better unsupervised segmentation performance compared to existing USS methods.
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization
In this paper, we propose a novel USS framework called Expand-and-Quantize Unsupervised Semantic Segmentation (EQUSS), which combines the benefits of high-dimensional spaces for better clustering and product quantization for effective information compression.
A Lightweight Clustering Framework for Unsupervised Semantic Segmentation
We thus propose a lightweight clustering framework for unsupervised semantic segmentation.
Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation
Self-supervised learning (SSL) can be used to solve complex visual tasks without human labels.
Overhead Line Defect Recognition Based on Unsupervised Semantic Segmentation
Overhead line inspection greatly benefits from defect recognition using visible light imagery.
Pixel-Level Clustering Network for Unsupervised Image Segmentation
Furthermore, we present an extension of the proposed method for unsupervised semantic segmentation.
Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling
We achieve this by (1) learning depth-feature correlation by spatially correlate the feature maps with the depth maps to induce knowledge about the structure of the scene and (2) implementing farthest-point sampling to more effectively select relevant features by utilizing 3D sampling techniques on depth information of the scene.
A Spatiotemporal Correspondence Approach to Unsupervised LiDAR Segmentation with Traffic Applications
We address the problem of unsupervised semantic segmentation of outdoor LiDAR point clouds in diverse traffic scenarios.
Learning Neural Eigenfunctions for Unsupervised Semantic Segmentation
Unsupervised semantic segmentation is a long-standing challenge in computer vision with great significance.
Removing supervision in semantic segmentation with local-global matching and area balancing
Our model attains state-of-the-art in Weakly Supervised Semantic Segmentation, only image-level labels, with 75% mIoU on PascalVOC2012 val set and 46% on MS-COCO2014 val set.
