Unsupervised Object Segmentation
21 papers with code • 9 benchmarks • 11 datasets
Benchmarks
These leaderboards are used to track progress in Unsupervised Object Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Datasets
DUTS
DAVIS 2016
FBMS
SegTrack-v2
ECSSD
Multi-dSprites
ClevrTex
FBMS-59
Latest papers
Benchmarking and Analysis of Unsupervised Object Segmentation from Real-world Single Images
We first introduce seven complexity factors to quantitatively measure the distributions of background and foreground object biases in appearance and geometry for datasets with human annotations.
SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers
Unsupervised object-centric learning aims to decompose scenes into interpretable object entities, termed slots.
Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping
TonyLianLong/RCF-UnsupVideoSeg
•
•
CVPR 2023
The Gestalt law of common fate, i. e., what move at the same speed belong together, has inspired unsupervised object discovery based on motion segmentation.
ILSGAN: Independent Layer Synthesis for Unsupervised Foreground-Background Segmentation
qrzou/ILSGAN
•
•
Unsupervised foreground-background segmentation aims at extracting salient objects from cluttered backgrounds, where Generative Adversarial Network (GAN) approaches, especially layered GANs, show great promise.
Promising or Elusive? Unsupervised Object Segmentation from Real-world Single Images
We firstly introduce four complexity factors to quantitatively measure the distributions of object- and scene-level biases in appearance and geometry for datasets with human annotations.
A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation
We propose a simple, yet powerful approach for unsupervised object segmentation in videos.
Refine and Represent: Region-to-Object Representation Learning
Recent works in self-supervised learning have demonstrated strong performance on scene-level dense prediction tasks by pretraining with object-centric or region-based correspondence objectives.
Segmenting Moving Objects via an Object-Centric Layered Representation
The objective of this paper is a model that is able to discover, track and segment multiple moving objects in a video.
Unsupervised Multi-object Segmentation Using Attention and Soft-argmax
We introduce a new architecture for unsupervised object-centric representation learning and multi-object detection and segmentation, which uses a translation-equivariant attention mechanism to predict the coordinates of the objects present in the scene and to associate a feature vector to each object.
EM-driven unsupervised learning for efficient motion segmentation
Etienne-Meunier-Inria/EM-Flow-Segmentation
•
•
The core idea of our work is to leverage the Expectation-Maximization (EM) framework in order to design in a well-founded manner a loss function and a training procedure of our motion segmentation neural network that does not require either ground-truth or manual annotation.
