Unsupervised Object Segmentation
8 papers with code • 3 benchmarks • 4 datasets
Benchmarks
| Trend | Dataset | Best Model | Paper Title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
Multi-dSprites
Greatest papers with code
Multi-Object Representation Learning with Iterative Variational Inference
deepmind/deepmind-research
•
•
Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities.
Unsupervised Object Segmentation by Redrawing
mickaelChen/ReDO
•
•
NeurIPS 2019
Object segmentation is a crucial problem that is usually solved by using supervised learning approaches over very large datasets composed of both images and corresponding object masks.
MONet: Unsupervised Scene Decomposition and Representation
deepmind/multi_object_datasets
•
•
The ability to decompose scenes in terms of abstract building blocks is crucial for general intelligence.
Object Segmentation Without Labels with Large-Scale Generative Models
anvoynov/BigGANsAreWatching
•
•
The recent rise of unsupervised and self-supervised learning has dramatically reduced the dependency on labeled data, providing effective image representations for transfer to downstream vision tasks.
GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement
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.
Ranked #1 on
Unsupervised Object Segmentation
on ObjectsRoom
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.
Ranked #1 on
Image Generation
on Multi-dSprites
Emergence of Object Segmentation in Perturbed Generative Models
adambielski/perturbed-seg
•
•
NeurIPS 2019
To force the generator to learn a representation where the foreground layer corresponds to an object, we perturb the output of the generative model by introducing a random shift of both the foreground image and mask relative to the background.
Object Discovery with a Copy-Pasting GAN
basilevh/object-discovery-cp-gan
•
•
We tackle the problem of object discovery, where objects are segmented for a given input image, and the system is trained without using any direct supervision whatsoever.