CoChat
Sign Up
Cited by 53Advanced Neural Network ApplicationsMedical Image Segmentation TechniquesDomain Adaptation and Few-Shot Learning

DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering

Open access
Aflalo, Amit, Bagon, Shai, Kashti, Tamar, Eldar, Yonina·2023·2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
DOI 10.1109/iccvw60793.2023.00010
Open this paper in CoChat — free accountOpen PDF

Abstract

Image segmentation is a fundamental task in computer vision. Data annotation for training supervised methods can be labor-intensive, motivating unsupervised methods. Current approaches often rely on extracting deep features from pre-trained networks to construct a graph, and classical clustering methods like k-means and normalized-cuts are then applied as a post-processing step. However, this approach reduces the high-dimensional information encoded in the features to pair-wise scalar affinities. To address this limitation, this study introduces a lightweight Graph Neural Network (GNN) to replace classical clustering methods while optimizing for the same clustering objective function. Unlike existing methods, our GNN takes both the pair-wise affinities between local image features and the raw features as input. This direct connection between the raw features and the clustering objective enables us to implicitly perform classification of the clusters between different graphs, resulting in part semantic segmentation without the need for additional post-processing steps. We demonstrate how classical clustering objectives can be formulated as self-supervised loss functions for training an image segmentation GNN. Furthermore, we employ the Correlation-Clustering (CC) objective to perform clustering without defining the number of clusters, allowing for k-less clustering. We apply the proposed method for object localization, segmentation, and semantic part segmentation tasks, surpassing state-of-the-art performance on multiple benchmarks1.

Integrity signals

Registry

Crossref · 10.1109/iccvw60793.2023.00010

Cites

35 of 35 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
Aflalo, A., Bagon, S., Kashti, T., & Eldar, Y.
Affiliations
Weizmann Institute of Science (IL)
ORCID
Venue
2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Publisher
IEEE
Published
2023-10-02
Pages
32-41
ISSN
2473-9936 (ISSN-L)
DOI
10.1109/iccvw60793.2023.00010
OpenAlex
W4390190093
Cited by
53
References
35
Citations by year
2026: 7 · 2025: 27 · 2024: 17 · 2023: 2
FWCI
5.68
Type
conference paper
Language
en
Open access
Licence
Locations
  • IEEE International Conference on Computer Vision Workshops (publishedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • arXiv (Cornell University) (cc-by)
Funders
  • European Commission (HORIZON2020)
  • Carolito Stiftung
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords
unsupervised image segmentation, graph neural networks, graph clustering, correlation clustering, object localization

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review