Unsupervised Image Segmentation
15 papers with code • 2 benchmarks • 4 datasets
Oxford 102 Flower
COCO-Stuff
BN-HTRd
TYC Dataset
Most implemented papers
W-Net: A Deep Model for Fully Unsupervised Image Segmentation
While significant attention has been recently focused on designing supervised deep semantic segmentation algorithms for vision tasks, there are many domains in which sufficient supervised pixel-level labels are difficult to obtain.
GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
applied-ai-lab/genesis
•
•
ICLR 2020
Generative latent-variable models are emerging as promising tools in robotics and reinforcement learning.
Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering
kanezaki/pytorch-unsupervised-segmentation-tip
•
•
The usage of convolutional neural networks (CNNs) for unsupervised image segmentation was investigated in this study.
GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement
applied-ai-lab/genesis
•
•
NeurIPS 2021
Moreover, object representations are often inferred using RNNs which do not scale well to large images or iterative refinement which avoids imposing an unnatural ordering on objects in an image but requires the a priori initialisation of a fixed number of object representations.
Improving Object-centric Learning with Query Optimization
The ability to decompose complex natural scenes into meaningful object-centric abstractions lies at the core of human perception and reasoning.
Salient object detection on hyperspectral images using features learned from unsupervised segmentation task
gqding/SUDF
•
•
Various saliency detection algorithms from color images have been proposed to mimic eye fixation or attentive object detection response of human observers for the same scenes.
Autoregressive Unsupervised Image Segmentation
Max-Manning/autoregunsupseg
•
•
ECCV 2020
In this work, we propose a new unsupervised image segmentation approach based on mutual information maximization between different constructed views of the inputs.
Information-Theoretic Segmentation by Inpainting Error Maximization
We study image segmentation from an information-theoretic perspective, proposing a novel adversarial method that performs unsupervised segmentation by partitioning images into maximally independent sets.
Unsupervised Hyperspectral Stimulated Raman Microscopy Image Enhancement: Denoising and Segmentation via One-Shot Deep Learning
CLEANit/SRS2021
•
•
Hyperspectral stimulated Raman scattering (SRS) microscopy is a label-free technique for biomedical and mineralogical imaging which can suffer from low signal to noise ratios.
RAMA: A Rapid Multicut Algorithm on GPU
pawelswoboda/rama
•
•
CVPR 2022
We propose a highly parallel primal-dual algorithm for the multicut (a. k. a.
