computer-vision-5

Unsupervised Object Segmentation

3260 papers • 126 benchmarks • 313 datasets

Image credit: ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in unsupervised-object-segmentation-5

Trend

Dataset

Best Model

Actions

ClevrTex

DAVIS 2016

SegTrack-v2

Libraries

i

Use these libraries to find unsupervised-object-segmentation-5 models and implementations

Datasets

Subtasks

No subtasks available.

Most implemented papers

Multi-Object Representation Learning with Iterative Variational Inference

M. Botvinick, Daniel Zoran, Christopher P. Burgess, L. Matthey, Nicholas Watters, Rishabh Kabra, Alexander Lerchner, Klaus Greff, Raphael Lopez Kaufman•Thu Feb 28 2019

This work argues for the importance of learning to segment and represent objects jointly, and demonstrates that, starting from the simple assumption that a scene is composed of multiple entities, it is possible to learn to segment images into interpretable objects with disentangled representations.

Content

FBMS-59

ShapeStacks

ObjectsRoom

Shelf&Tote Training Dataset

DUTS

ECSSD

ClevrTex

ShapeStacks

FBMS-59

ObjectsRoom

546

0

Paper Graph

MONet: Unsupervised Scene Decomposition and Representation

M. Botvinick, Christopher P. Burgess, L. Matthey, Nicholas Watters, Rishabh Kabra, I. Higgins, Alexander Lerchner•Mon Jan 21 2019

The Multi-Object Network (MONet) is developed, which is capable of learning to decompose and represent challenging 3D scenes into semantically meaningful components, such as objects and background elements.

574 0

Paper Graph

GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement

I. Posner, Martin Engelcke, Oiwi Parker Jones•Mon Apr 19 2021

This work proposes an embedding-based approach in which embeddings of pixels are clustered in a differentiable fashion using a stochastic stick-breaking process to develop a new model, GENESIS-v2, which can infer a variable number of object representations without using RNNs or iterative refinement.

133 0

Paper Graph

GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations

I. Posner, Martin Engelcke, Adam R. Kosiorek, Oiwi Parker Jones•Mon Jul 29 2019

Generative latent-variable models are emerging as promising tools in robotics and reinforcement learning. Yet, even though tasks in these domains typically involve distinct objects, most state-of-the-art generative models do not explicitly capture the compositional nature of visual scenes. Two recent exceptions, MONet and IODINE, decompose scenes into objects in an unsupervised fashion. Their underlying generative processes, however, do not account for component interactions. Hence, neither of them allows for principled sampling of novel scenes. Here we present GENESIS, the first object-centric generative model of 3D visual scenes capable of both decomposing and generating scenes by capturing relationships between scene components. GENESIS parameterises a spatial GMM over images which is decoded from a set of object-centric latent variables that are either inferred sequentially in an amortised fashion or sampled from an autoregressive prior. We train GENESIS on several publicly available datasets and evaluate its performance on scene generation, decomposition, and semi-supervised learning.

327 0

Paper Graph

Unsupervised Image Decomposition with Phase-Correlation Networks

Sven Behnke, Angel Villar-Corrales•Wed Oct 06 2021

The Phase-Correlation Decomposition Network (PCDNet), a novel model that decomposes a scene into its object components, which are represented as transformed versions of a set of learned object prototypes, is proposed.

5 0

Paper Graph

Object Discovery with a Copy-Pasting GAN

Andrew Zisserman, Relja Arandjelović•Sun May 26 2019

A novel copy-pasting GAN framework is proposed, where the generator learns to discover an object in one image by compositing it into another image such that the discriminator cannot tell that the resulting image is fake.

58 0

Paper Graph

Unsupervised Object Segmentation by Redrawing

T. Artières, Ludovic Denoyer, Mickaël Chen•Sun May 26 2019

ReDO is presented, a new model able to extract objects from images without any annotation in an unsupervised way based on the idea that it should be possible to change the textures or colors of the objects without changing the overall distribution of the dataset.

147 0

Paper Graph

Emergence of Object Segmentation in Perturbed Generative Models

P. Favaro, Adam Bielski•Tue Apr 30 2019

A novel framework to build a model that can learn how to segment objects from a collection of images without any human annotation is introduced, based on the observation that the location of object segments can be perturbed locally relative to a given background without affecting the realism of a scene.

105 0

Paper Graph

Object Segmentation Without Labels with Large-Scale Generative Models

Artem Babenko, S. Morozov, A. Voynov•Sun Jun 07 2020

This work demonstrates that large-scale unsupervised models can also perform a more challenging object segmentation task, requiring neither pixel-level nor image-level labeling, achieving new state-of-the-art results.

67 0

Paper Graph

The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos

Stephen Lin, Stella X. Yu, Runtao Liu, Zhirong Wu•Wed Nov 10 2021

This work is the first truly end-to-end zero-shot object segmentation from videos and develops generic objectness for segmentation and tracking, but also outperforms prevalent image-based contrastive learning methods without augmentation engineering.

59 0

Paper Graph

Adding a benchmark result helps the community track progress.